© 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. 95642
    Prev
    Next
    INDEX
    Explanations

    legal, or travel specifics

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

    not like I

    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
     ched
    0.48
    妽
    0.46
     curricula
    0.46
    䟺
    0.45
     Phosphate
    0.45
     constitutions
    0.44
     dehydrogen
    0.43
    砶
    0.43
     $\
    0.43
    odymium
    0.43
    POSITIVE LOGITS
    anj
    0.43
    pandas
    0.43
    nání
    0.43
    crm
    0.42
    jän
    0.41
    inje
    0.41
    én
    0.41
    مله
    0.40
    pac
    0.40
    insurance
    0.40
    Activations Density 0.000%

    No Known Activations