© 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. 34-GEMMASCOPE-RES-131K
    7. 31975
    Prev
    Next
    INDEX
    Explanations

    indictments or charging citizens

    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_34/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
     consort
    -0.79
    itres
    -0.69
     clasp
    -0.67
    Rory
    -0.66
     駐
    -0.66
     Planting
    -0.65
     чесно
    -0.65
    NSY
    -0.63
    чке
    -0.62
     TRS
    -0.62
    POSITIVE LOGITS
     indictment
    3.30
     indict
    2.50
     indicted
    2.14
     Ind
    1.80
    ind
    1.67
     indic
    1.45
     grand
    1.44
    Ind
    1.42
     IND
    1.41
     charging
    1.38
    Activations Density 0.060%

    No Known Activations