© 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. 9500
    Prev
    Next
    INDEX
    Explanations

    seeing what is happening

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

    sentence endings

    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
    嘍
    0.57
     आजकल
    0.55
     আজকাল
    0.53
    喽
    0.52
    Caracter
    0.51
    pèce
    0.48
    apanicolaou
    0.48
     whatnot
    0.47
     ständig
    0.46
     מת
    0.46
    POSITIVE LOGITS
     unequivocally
    0.54
     efectivamente
    0.53
     UK
    0.51
     crucially
    0.51
    我认为
    0.48
     genuinely
    0.48
     F
    0.48
     വിമ
    0.48
     Modelling
    0.47
    请
    0.47
    Activations Density 0.023%

    No Known Activations