© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 13102
    Prev
    Next
    INDEX
    Explanations

    am and pm time expressions

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

    risk, phase, chemical action

    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
    psp
    0.53
    cps
    0.46
    z
    0.44
    상은
    0.43
    つ
    0.43
    wicket
    0.42
    པ
    0.41
     confront
    0.40
     immort
    0.40
    кать
    0.40
    POSITIVE LOGITS
    TimeDict
    0.49
     ผ้า
    0.47
     détail
    0.45
    íbrio
    0.44
    䉽
    0.44
     dettaglio
    0.44
     Holidays
    0.43
    ッと
    0.43
    ्तार
    0.43
    ategories
    0.43
    Activations Density 0.001%

    No Known Activations