© 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. 31858
    Prev
    Next
    INDEX
    Explanations

    attached to a house

    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
    dayspecial
    1.14
     attachments
    1.13
     т
    1.07
     avión
    1.07
     ваше
    1.06
     całkow
    1.06
     օ
    1.05
    <unused2130>
    1.05
    attachments
    1.04
     pavattati
    1.04
    POSITIVE LOGITS
    g
    1.45
    ing
    1.41
    ed
    1.28
    is
    1.23
    as
    1.21
    e
    1.16
    v
    1.16
    in
    1.16
    p
    1.16
    un
    1.15
    Activations Density 0.003%

    No Known Activations