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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 53058
    Prev
    Next
    INDEX
    Explanations

    color, trade, past, technology, code, currency, date

    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
    geben
    0.50
    OGRAP
    0.48
    +](=
    0.46
    みが
    0.46
     REGIUNI
    0.46
    ULTURAL
    0.45
    racción
    0.45
     मद्देन
    0.44
     ಕೊಟ್ಟ
    0.44
     świę
    0.44
    POSITIVE LOGITS
     bitrate
    0.48
     in
    0.46
    。
    0.44
     post
    0.44
     medium
    0.41
     partner
    0.41
     Finally
    0.41
     tag
    0.41
     buffer
    0.41
     salary
    0.41
    Activations Density 0.000%

    No Known Activations