© 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. 135310
    Prev
    Next
    INDEX
    Explanations

    foreign language identifiers

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

    made me, making me, become clear

    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
    ATCH
    0.49
    ussel
    0.47
     aldığı
    0.45
     groves
    0.44
     _{\
    0.44
     bask
    0.44
     probs
    0.44
     apron
    0.43
     섬
    0.43
     atmospheres
    0.43
    POSITIVE LOGITS
     codice
    0.47
    农
    0.46
    ן
    0.45
    اور
    0.44
    を通じて
    0.44
    ਕਰ
    0.44
    スター
    0.42
    تبقى
    0.42
    報酬
    0.42
    が出
    0.42
    Activations Density 0.002%

    No Known Activations