© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35163
    Prev
    Next
    INDEX
    Explanations

    page numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     biografia
    -1.52
     furia
    -1.44
     polícia
    -1.38
    がありますが
    -1.38
    ONLY
    -1.36
     conster
    -1.36
    vedať
    -1.32
    pleft
    -1.32
     prefeito
    -1.32
    特長
    -1.31
    POSITIVE LOGITS
    7
    1.64
    9
    1.52
    3
    1.50
    0
    1.40
    8
    1.35
    6
    1.30
    4
    1.27
    5
    1.25
     and
    1.24
    varlak
    1.18
    Activations Density 0.009%

    No Known Activations