© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52414
    Prev
    Next
    INDEX
    Explanations

    survival and construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chua
    0.46
     Expedia
    0.46
     umbrella
    0.44
     unsuspecting
    0.44
    匯
    0.43
    ের
    0.42
    matching
    0.42
     patriotic
    0.41
     with
    0.41
    ская
    0.41
    POSITIVE LOGITS
     Verhalten
    0.47
     죽
    0.44
     chapitre
    0.43
     అమె
    0.42
    перыі
    0.42
     Восто
    0.42
     Современ
    0.42
     애니
    0.41
     Algebras
    0.41
     വർ
    0.41
    Activations Density 0.003%

    No Known Activations