© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 317
    Prev
    Next
    INDEX
    Explanations

    starts of phrases or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    睨
    1.08
    ceeded
    1.02
    肇
    1.00
     transgress
    0.94
    に向け
    0.93
    渾
    0.92
     embroiled
    0.91
    stimulated
    0.89
     swipes
    0.88
     ravaged
    0.88
    POSITIVE LOGITS
    >>>
    1.75
     vraiment
    1.65
    κι
    1.64
    Why
    1.61
    購買
    1.61
     jednoduch
    1.61
     такое
    1.60
    ؟
    1.59
    ⟹
    1.59
     nên
    1.58
    Activations Density 0.487%

    No Known Activations