© 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. 60987
    Prev
    Next
    INDEX
    Explanations

    by team numbers

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

    direct causes

    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
    ă
    0.46
    lą
    0.45
    atura
    0.44
    ening
    0.44
    vania
    0.44
    vature
    0.44
    setLocation
    0.44
    initely
    0.43
     powodu
    0.43
     ט
    0.42
    POSITIVE LOGITS
    στι
    0.50
     preclinical
    0.46
    第三
    0.46
    च्युअल
    0.44
    ிகா
    0.43
    zględ
    0.43
    γεν
    0.43
    쇤
    0.43
    PAD
    0.43
    蓓
    0.42
    Activations Density 0.001%

    No Known Activations