© 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. 124175
    Prev
    Next
    INDEX
    Explanations

    deceptions

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

    mean square error

    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
     Cube
    0.46
     시스템
    0.45
    鈕
    0.44
    시스템
    0.44
    యం
    0.44
    Cube
    0.43
    arser
    0.43
    νοι
    0.43
     সাধারণভাবে
    0.42
    μοί
    0.42
    POSITIVE LOGITS
    lp
    0.48
    Trav
    0.46
     gypsy
    0.46
    mother
    0.45
    妊
    0.44
    Gy
    0.44
    Ｃ
    0.44
    Jan
    0.43
    Javascript
    0.43
    having
    0.43
    Activations Density 0.001%

    No Known Activations