© 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. 148579
    Prev
    Next
    INDEX
    Explanations

    drug addiction history

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

    cyclical process, referring to objects

    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
    ה
    0.58
    트
    0.52
    ת
    0.51
    이크
    0.48
    Disclaimer
    0.48
     губернатора
    0.47
    目光
    0.46
    你应该
    0.46
    osław
    0.46
    InvalidArgument
    0.46
    POSITIVE LOGITS
    2
    0.54
     entre
    0.44
     orig
    0.44
     Sharing
    0.43
    provide
    0.43
    deriv
    0.42
     arred
    0.42
     origem
    0.41
     to
    0.41
    </div>
    0.40
    Activations Density 0.000%

    No Known Activations