© 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. 41718
    Prev
    Next
    INDEX
    Explanations

    hence object & existing

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

    tax implications parts classification construction

    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
     ук
    0.43
    甫
    0.42
    ໂດ
    0.41
    IGNED
    0.41
    adians
    0.41
    ভৃতি
    0.40
     описание
    0.40
    𝙶
    0.40
     जिन्होंने
    0.40
    场的
    0.40
    POSITIVE LOGITS
     dispositif
    0.46
    bahnhof
    0.44
     indeks
    0.44
     igaz
    0.43
    political
    0.43
     Oktober
    0.42
    matter
    0.41
    useum
    0.41
     Hersteller
    0.40
     verfol
    0.40
    Activations Density 0.000%

    No Known Activations