© 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. 169468
    Prev
    Next
    INDEX
    Explanations

    survey, amount, limits, celebrate, accepted, ensuring

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

    qualifications and clarifications

    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
     나올
    0.44
     dz
    0.44
    }
    0.43
    山东
    0.43
    存在的
    0.43
     इसके
    0.43
     uninstall
    0.42
    мии
    0.42
     Correctional
    0.42
    统治
    0.42
    POSITIVE LOGITS
    פר
    0.45
    Ấ
    0.44
    роз
    0.43
    CLASSI
    0.43
     vuttam
    0.43
    кова
    0.43
    ilikom
    0.43
    كبر
    0.42
    ד
    0.42
    PARAMETERS
    0.42
    Activations Density 0.000%

    No Known Activations