© 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. 34-GEMMASCOPE-RES-131K
    7. 63217
    Prev
    Next
    INDEX
    Explanations

    `Q` after numbers or `.`

    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
     Mudah
    -0.89
    UNIC
    -0.87
     falt
    -0.81
     navideña
    -0.81
    እ
    -0.79
     unidentified
    -0.79
     sandalwood
    -0.79
     EXPERIMENT
    -0.79
    #@
    -0.78
     Caro
    -0.78
    POSITIVE LOGITS
     visit
    0.85
    <>();
    0.84
     map
    0.84
     cost
    0.83
     usado
    0.81
    Map
    0.80
    zner
    0.79
     StringBuilder
    0.78
     haremos
    0.77
     COST
    0.77
    Activations Density 0.000%

    No Known Activations