© 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. 127254
    Prev
    Next
    INDEX
    Explanations

    joy and media insight

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

    secret personality or important qualities

    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
    എം
    0.56
    ವಾಗಿ
    0.50
    所謂
    0.49
    ț
    0.49
    ہ
    0.49
    ता
    0.48
    에서의
    0.48
    ї
    0.47
     пове
    0.46
    बंधनाच्या
    0.45
    POSITIVE LOGITS
     φα
    0.53
    oscope
    0.49
     encontrado
    0.47
    দ্বার
    0.45
    Ticker
    0.45
    Scaling
    0.45
    Prepare
    0.43
    scaled
    0.43
    UInteger
    0.43
    Large
    0.42
    Activations Density 0.000%

    No Known Activations