© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 236219
    Prev
    Next
    INDEX
    Explanations

    online search service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    上演
    0.45
    價
    0.45
    pricing
    0.45
     উৎপ
    0.44
    政府
    0.43
    殄
    0.43
    ૂ
    0.43
    branding
    0.42
    創造
    0.42
    阿
    0.41
    POSITIVE LOGITS
     delim
    0.46
     nécessaire
    0.46
     much
    0.45
     jeśli
    0.44
     skates
    0.44
     ful
    0.43
     akkor
    0.43
     anno
    0.42
     seu
    0.42
    iędzy
    0.42
    Activations Density 0.001%

    No Known Activations