© 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. 1893
    Prev
    Next
    INDEX
    Explanations

    so followed by explanation

    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
     I
    0.20
    there
    0.20
     THINGS
    0.18
     things
    0.18
    a
    0.18
    the
    0.18
    由于
    0.18
     因為
    0.18
     dingen
    0.17
     we
    0.17
    POSITIVE LOGITS
     важно
    0.22
     گرفتن
    0.21
    ening
    0.17
     seeming
    0.16
     مهم
    0.16
     derfor
    0.16
    ،
    0.16
     stressful
    0.15
    سبوع
    0.15
    প্রসঙ্গত
    0.15
    Activations Density 0.167%

    No Known Activations