© 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. 37013
    Prev
    Next
    INDEX
    Explanations

    06 June

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

    code directives and state saving

    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
    も
    0.51
     mutilated
    0.44
     scab
    0.41
     RATE
    0.41
    ವಾಡ
    0.41
    தால்
    0.40
    도
    0.40
     لي
    0.39
     ASTM
    0.39
     weaning
    0.39
    POSITIVE LOGITS
    iku
    0.44
     особое
    0.44
     riječi
    0.44
    res
    0.43
    řej
    0.43
    द्दा
    0.43
    {
    0.43
     Gson
    0.42
    ȏ
    0.41
    arik
    0.41
    Activations Density 0.000%

    No Known Activations