© 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. 134355
    Prev
    Next
    INDEX
    Explanations

    steal big, steal less

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

    fast chat

    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
     None
    0.59
    KEY
    0.52
     KOH
    0.50
     органов
    0.49
     ທ
    0.49
    KOH
    0.48
     ಎರಡ
    0.47
     FutureWarning
    0.47
     элемент
    0.47
    OLD
    0.46
    POSITIVE LOGITS
    다는
    0.49
    цент
    0.47
    дай
    0.46
    cando
    0.45
    safety
    0.44
    люс
    0.44
     mets
    0.42
    cited
    0.42
    icu
    0.42
    泉
    0.41
    Activations Density 0.000%

    No Known Activations