© 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. 158637
    Prev
    Next
    INDEX
    Explanations

    likely to or solutions provider

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

    identity, risk, or inclusion

    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
    ramique
    0.48
     Тру
    0.47
    밉
    0.45
    ראה
    0.45
    反
    0.44
    ρών
    0.44
    常に
    0.44
     수상
    0.44
    前
    0.43
    <0xE3>
    0.42
    POSITIVE LOGITS
     commentaries
    0.47
     irregularities
    0.44
     Rhythm
    0.44
    í
    0.44
     weaves
    0.43
     inhomogeneities
    0.43
     Link
    0.43
     وز
    0.43
    REZ
    0.42
    akti
    0.42
    Activations Density 0.000%

    No Known Activations