© 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. 65215
    Prev
    Next
    INDEX
    Explanations

    their positions

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

    emotional distress and harm

    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
    
    0.53
    *;
    0.50
    ;
    0.50
     будут
    0.50
    »;
    0.48
    %;
    0.47
     estarán
    0.47
     список
    0.46
     símbolo
    0.45
    TypeList
    0.45
    POSITIVE LOGITS
    ಲ್ಲು
    0.50
    aders
    0.46
    tanh
    0.45
     Appearance
    0.44
     광
    0.43
    adig
    0.43
    odo
    0.43
    ুদ
    0.43
    anud
    0.42
    adis
    0.42
    Activations Density 0.000%

    No Known Activations