© 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. 40-GEMMASCOPE-2-RES-262K
    7. 111128
    Prev
    Next
    INDEX
    Explanations

    sort, baby, harm

    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_40_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
    她说
    0.45
    Ἔ
    0.41
    ียด
    0.40
    iru
    0.38
     spectacles
    0.38
    ிரம்
    0.38
    Toolbar
    0.37
    溉
    0.36
    聞
    0.36
    قاف
    0.36
    POSITIVE LOGITS
     divide
    0.42
     dividers
    0.40
     piv
    0.39
     hair
    0.39
     GCD
    0.39
     Additional
    0.38
     neutrality
    0.38
     winds
    0.38
     Relative
    0.38
     marriage
    0.38
    Activations Density 0.000%

    No Known Activations