© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4346
    Prev
    Next
    INDEX
    Explanations

    George and a surname

    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_16_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
    1
    1.68
    ut
    1.63
    as
    1.51
    ك
    1.23
     on
    1.20
    aré
    1.20
    ع
    1.17
    एस
    1.15
    การ
    1.13
    an
    1.09
    POSITIVE LOGITS
    ли
    1.88
    л
    1.40
    મ
    1.30
    <0x80>
    1.21
    ர
    1.21
    х
    1.20
    я
    1.20
    pe
    1.13
    ă
    1.13
    ன்
    1.13
    Activations Density 0.025%

    No Known Activations