© 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. 98143
    Prev
    Next
    INDEX
    Explanations

    legal and financial advice

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

    uncover or gain knowledge

    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
    arán
    0.52
    erapia
    0.47
    %。
    0.46
    )。
    0.45
    sampled
    0.44
    "。
    0.44
    亦
    0.43
     संचालन
    0.43
    ానని
    0.42
    ）。
    0.41
    POSITIVE LOGITS
     નવા
    0.40
    emade
    0.40
    стар
    0.40
     fang
    0.40
     използ
    0.40
     материалы
    0.39
     fragmented
    0.39
    方は
    0.39
     flimsy
    0.39
    உ
    0.39
    Activations Density 0.000%

    No Known Activations