© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 95864
    Prev
    Next
    INDEX
    Explanations

    additional commands

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

    security and fraud

    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
    Kp
    0.46
    A
    0.46
    Expansion
    0.44
    ,]
    0.43
    Aw
    0.43
    ByURL
    0.43
     Kt
    0.42
    を発
    0.42
     свър
    0.42
    ആര്‍
    0.42
    POSITIVE LOGITS
    ла
    0.55
    엷
    0.52
    벵
    0.51
    ड़ब
    0.50
    حية
    0.48
    罹
    0.48
    ثر
    0.48
     opportunità
    0.47
    لد
    0.46
     modalités
    0.46
    Activations Density 0.000%

    No Known Activations