© 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. 39809
    Prev
    Next
    INDEX
    Explanations

    shared links and specific observations

    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
    <0x80>
    0.53
     ১৬
    0.49
    使う
    0.48
    ０
    0.48
     மில்லியன்
    0.47
    жным
    0.47
     millió
    0.47
    scrire
    0.47
    дан
    0.47
    ॅमिली
    0.47
    POSITIVE LOGITS
    +
    0.52
     closes
    0.51
     energy
    0.50
     chemical
    0.49
     chem
    0.47
     concentration
    0.46
     twilight
    0.46
     সত্ত
    0.45
    (@
    0.45
     metaphysical
    0.44
    Activations Density 0.001%

    No Known Activations