© 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. 178882
    Prev
    Next
    INDEX
    Explanations

    my father, company

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

    often followed by words regarding options or common occurrences

    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
    تي
    0.48
     নান
    0.48
    ጀ
    0.47
    4
    0.45
     se
    0.44
     sanitized
    0.44
     sobald
    0.43
    زا
    0.43
    తి
    0.41
    شم
    0.41
    POSITIVE LOGITS
     Stephens
    0.52
     underval
    0.51
     omission
    0.49
     Billings
    0.48
    payer
    0.47
     interleaved
    0.47
     emphasis
    0.47
    ptive
    0.47
    omit
    0.47
    滀
    0.46
    Activations Density 0.001%

    No Known Activations