© 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. 173326
    Prev
    Next
    INDEX
    Explanations

    reproduced, recorded, story, body, sensors

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

    list of immediate opportunities

    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
     cunning
    0.48
     კ
    0.47
     trium
    0.45
     favorit
    0.44
     نو
    0.44
     stature
    0.44
     collusion
    0.43
     نسخه
    0.43
     elucidation
    0.43
     liste
    0.43
    POSITIVE LOGITS
    २
    0.48
    时间
    0.47
    Age
    0.45
    Requires
    0.45
    started
    0.44
    पिछले
    0.43
    इसलिए
    0.43
    week
    0.43
    ীব
    0.42
    Maryland
    0.42
    Activations Density 0.000%

    No Known Activations