© 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-262K
    4. 50979
    Prev
    Next
    INDEX
    Explanations

    control and restrictions

    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
    ח
    0.50
    Méd
    0.43
    ट
    0.42
    也要
    0.42
    serviceTime
    0.42
    Transl
    0.42
    ד
    0.42
    ק
    0.42
    乘
    0.41
    宏
    0.41
    POSITIVE LOGITS
     Inquisition
    0.45
    ありました
    0.45
     restrictions
    0.45
     IQ
    0.45
     ਪਰ
    0.44
     the
    0.44
    gag
    0.43
    kommt
    0.43
     balconies
    0.42
     ISPs
    0.42
    Activations Density 0.006%

    No Known Activations