© 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. 33876
    Prev
    Next
    INDEX
    Explanations

    this. and self

    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
    struzioni
    -1.10
     Einige
    -1.02
     حتی
    -0.96
    ierte
    -0.96
     unbedingt
    -0.91
    сь
    -0.90
     конструкция
    -0.89
    荭
    -0.89
     поскольку
    -0.88
     raggiungere
    -0.88
    POSITIVE LOGITS
    =}
    0.98
     intensif
    0.98
    )$/,
    0.96
    0.96
    𝟐
    0.94
    ₱
    0.91
    ∅
    0.90
    ⁷
    0.90
    瓒
    0.90
     sembl
    0.89
    Activations Density 0.004%

    No Known Activations