© 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-65K
    7. 56989
    Prev
    Next
    INDEX
    Explanations

    hearing words associated with violence

    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
    நெ
    0.49
     interação
    0.49
    蛩
    0.46
    始まり
    0.46
    น์
    0.46
    échange
    0.46
    LEFT
    0.46
     TRANSFER
    0.45
     Gründung
    0.45
     início
    0.44
    POSITIVE LOGITS
     appropriate
    0.57
    。
    0.44
    the
    0.43
     amy
    0.43
     abortions
    0.43
     patriotic
    0.42
     dra
    0.42
    ）。
    0.41
     aggravating
    0.41
     implied
    0.41
    Activations Density 0.004%

    No Known Activations