© 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. 91887
    Prev
    Next
    INDEX
    Explanations

    new, fresh

    np_acts-logits-general · gemini-2.5-flash-lite

    not reinventing the wheel

    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
    memo
    0.43
    पार
    0.42
     сложные
    0.42
    कीपर
    0.41
     दब
    0.41
     действу
    0.40
     Крим
    0.40
    湋
    0.38
    வியல்
    0.37
     fileSize
    0.37
    POSITIVE LOGITS
    新規
    0.88
     afresh
    0.87
     anew
    0.86
    新たに
    0.84
    新鮮
    0.83
     newbies
    0.78
     fresh
    0.75
     புதி
    0.75
    陌生
    0.74
    全新
    0.73
    Activations Density 0.373%

    No Known Activations