© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62646
    Prev
    Next
    INDEX
    Explanations

    entry-level and specific terms

    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_65k_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
    }=\{\
    0.41
     Θε
    0.41
    AppCompatTheme
    0.40
    就會
    0.40
    依法
    0.39
     کورٹ
    0.39
     Handwriting
    0.39
    fromJson
    0.38
    豺
    0.38
    这件事
    0.38
    POSITIVE LOGITS
     marques
    0.46
    al
    0.43
     utama
    0.43
    seeds
    0.42
    poč
    0.42
    princess
    0.42
    swering
    0.41
    ኋላ
    0.41
     haupt
    0.41
     materiales
    0.40
    Activations Density 0.004%

    No Known Activations