© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13796
    Prev
    Next
    INDEX
    Explanations

    Google Wiki Worth advantage animal Jam offer

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

    spiritual beliefs and 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_16k_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
     (
    0.22
    (
    0.20
    ଂ
    0.20
    <b>
    0.20
    on
    0.19
     and
    0.19
    OGR
    0.19
    /
    0.18
    w
    0.18
    \'
    0.18
    POSITIVE LOGITS
     Якщо
    0.18
     கொரோனா
    0.18
     الخمسه
    0.18
     سایر
    0.17
     Mitarbeiter
    0.16
     dessin
    0.16
     Hvis
    0.16
     ٹرسٹ
    0.16
    இந்த
    0.16
     diğer
    0.16
    Activations Density 0.010%

    No Known Activations