© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 52805
    Prev
    Next
    INDEX
    Explanations

    marketing, caution, or physics descriptions

    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
    膿
    0.46
    懟
    0.46
     シンプル
    0.45
    똥
    0.43
    ction
    0.42
    徫
    0.42
    竴
    0.41
    釟
    0.41
    ܸ
    0.41
    気分
    0.40
    POSITIVE LOGITS
     promo
    0.45
     Absence
    0.44
     English
    0.42
     marketable
    0.42
     Promo
    0.42
     caution
    0.41
     Wear
    0.40
    Unary
    0.40
     unary
    0.40
     Origin
    0.40
    Activations Density 0.005%

    No Known Activations