© 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. 174730
    Prev
    Next
    INDEX
    Explanations

    Here is a

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

    defining question, score, parent

    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
    }}$-
    0.49
     produksi
    0.46
     islands
    0.45
     विधानसभा
    0.44
     yoğun
    0.44
    泊
    0.43
     universidades
    0.42
    aaS
    0.42
     refineries
    0.42
     embark
    0.42
    POSITIVE LOGITS
     Jacket
    0.45
     Scoop
    0.45
     Dewey
    0.45
    Condition
    0.44
    بوب
    0.44
     Dixon
    0.44
     Heb
    0.44
    條件
    0.43
    },
    0.43
    看的
    0.43
    Activations Density 0.000%

    No Known Activations