© 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. 31523
    Prev
    Next
    INDEX
    Explanations

    max length or max value

    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
     maximum
    -0.89
     not
    -0.84
    ādi
    -0.83
     Not
    -0.79
    していますが
    -0.79
     section
    -0.78
    际
    -0.76
     максима
    -0.74
     υπάρχ
    -0.73
     which
    -0.71
    POSITIVE LOGITS
    Į
    0.82
    ophobic
    0.80
    wg
    0.79
    ʉ
    0.79
    ناک
    0.79
    Soft
    0.77
    .=
    0.77
    =“
    0.77
    βο
    0.77
    LH
    0.77
    Activations Density 0.002%

    No Known Activations