© 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. 241888
    Prev
    Next
    INDEX
    Explanations

    services by phone number

    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
     rote
    0.41
     υ
    0.39
     textColor
    0.39
     Tenure
    0.38
     ENC
    0.38
    runtime
    0.38
     tanned
    0.38
     degr
    0.38
    ầng
    0.38
     Butterworth
    0.38
    POSITIVE LOGITS
     respuesta
    0.51
     réponse
    0.50
    นาด
    0.48
     respuestas
    0.48
     پزش
    0.48
    ジオ
    0.48
    絆
    0.48
    璋
    0.47
    حث
    0.47
     risposta
    0.47
    Activations Density 0.000%

    No Known Activations