© 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. 186280
    Prev
    Next
    INDEX
    Explanations

    than drugs

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

    route, distance, vitamin K, MVP, XXI

    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
    略
    0.45
    Girls
    0.45
    Photo
    0.44
    S
    0.44
    版权
    0.43
    恋
    0.43
    ObjectType
    0.43
    ़
    0.42
    Written
    0.42
    Allen
    0.42
    POSITIVE LOGITS
    othérapie
    0.51
    eper
    0.48
     منهم
    0.46
    }_{+}\
    0.46
     dominions
    0.45
    }}+\
    0.45
    }_{+}
    0.43
     ascertained
    0.43
     pé
    0.43
     इन्हे
    0.43
    Activations Density 0.000%

    No Known Activations