© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28224
    Prev
    Next
    INDEX
    Explanations

    disapproval, worry, or silence

    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
    laan
    0.61
    alliative
    0.54
    uk
    0.53
    <0x94>
    0.52
    oxyl
    0.52
    eliti
    0.52
    îtes
    0.51
    Login
    0.50
    ac
    0.50
    ô
    0.49
    POSITIVE LOGITS
     عن
    0.48
    動
    0.47
     kink
    0.44
     tentang
    0.44
     centro
    0.43
     diagnose
    0.42
     чаще
    0.42
    恶
    0.42
     portrait
    0.42
     expose
    0.41
    Activations Density 0.002%

    No Known Activations