© 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. 71993
    Prev
    Next
    INDEX
    Explanations

    friend, editor, than, increase, some

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

    facts or descriptions

    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
    आर
    0.49
    ència
    0.46
    较大
    0.45
    ajari
    0.44
    寫
    0.44
    십
    0.43
    ஆர்
    0.43
    iliśmy
    0.42
     그러면은
    0.42
     ಆರ್
    0.41
    POSITIVE LOGITS
     hả
    0.53
     ceux
    0.52
     to
    0.51
     "'
    0.49
     ">
    0.47
     "...
    0.45
     "`
    0.44
     некоторых
    0.44
     "_
    0.44
     Rural
    0.43
    Activations Density 0.000%

    No Known Activations