© 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-65K
    7. 7131
    Prev
    Next
    INDEX
    Explanations

    problem solving instruction rule question

    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_65k_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
     is
    0.45
     on
    0.41
     makes
    0.37
     (
    0.36
     în
    0.36
    は
    0.36
     있는
    0.35
     pushed
    0.35
    வ்வளவு
    0.35
     describes
    0.35
    POSITIVE LOGITS
     and
    0.48
    性和
    0.44
    性と
    0.44
     एवं
    0.43
    和服务
    0.41
     και
    0.39
    ocratic
    0.39
    ‐
    0.39
    وە
    0.38
    及ひ
    0.38
    Activations Density 0.137%

    No Known Activations