© 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. 9700
    Prev
    Next
    INDEX
    Explanations

    sensitive to specific words and functions

    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
    État
    0.37
    सभी
    0.34
    ส
    0.33
     એપ્
    0.33
    Nationality
    0.32
    情报
    0.32
    ऍ
    0.31
    ammlung
    0.31
    inté
    0.31
     사업
    0.31
    POSITIVE LOGITS
     water
    0.33
     Emergency
    0.32
     emergency
    0.30
     so
    0.30
     low
    0.30
     preprocessing
    0.30
     When
    0.30
     Left
    0.30
     
    0.30
     non
    0.29
    Activations Density 0.087%

    No Known Activations