© 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. 130218
    Prev
    Next
    INDEX
    Explanations

    media followed by descriptor

    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
    E
    -2.63
    ();
    -2.59
    ");
    -2.59
    J
    -2.41
    .”
    -2.34
    I
    -2.34
    also
    -2.28
    ].
    -2.23
     Also
    -2.23
     Mitarbeitern
    -2.16
    POSITIVE LOGITS
    鹟
    2.83
    狆
    2.58
    嘁
    2.48
    嗞
    2.41
    龗
    2.27
    我們的
    2.27
    起きた
    2.22
    
    2.20
    猡
    2.20
     ответил
    2.20
    Activations Density 0.021%

    No Known Activations