© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34230
    Prev
    Next
    INDEX
    Explanations

    government actions and policies

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on mentions of government institutions or authorities (e.g. “government,” “Centre,” “Federal Government”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonsoft
    -1.52
    atação
    -1.34
    glTex
    -1.23
    (!__
    -1.21
     unſ
    -1.20
     oscuridad
    -1.20
    DebuggerNonUser
    -1.19
    AnchorStyles
    -1.18
    饧
    -1.17
    chnung
    -1.16
    POSITIVE LOGITS
     government
    1.59
     Government
    1.23
     response
    1.23
    ’
    1.18
     portátiles
    1.15
    ↵↵
    1.09
     الحكومة
    1.09
     espectro
    1.05
    government
    1.05
     including
    1.04
    Activations Density 0.032%

    No Known Activations