© 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. 116466
    Prev
    Next
    INDEX
    Explanations

    how longsave moneymajor wind

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

    AI tools

    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
     जूते
    0.51
    리기
    0.46
     Curtis
    0.46
     Hamlin
    0.46
    _:
    0.46
    ritten
    0.45
     Bevan
    0.45
    कोड
    0.45
    ലെസ്
    0.45
    BUT
    0.44
    POSITIVE LOGITS
    ό
    0.50
    回应
    0.48
     interno
    0.46
     मलया
    0.46
    ि
    0.46
     políticas
    0.45
     extranj
    0.45
    大
    0.45
    σό
    0.45
     aeros
    0.44
    Activations Density 0.000%

    No Known Activations