© 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. 108577
    Prev
    Next
    INDEX
    Explanations

    within or between variation

    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
    oppers
    0.44
    ଅ
    0.43
     대부분
    0.42
    ösung
    0.41
    ješ
    0.41
    ос
    0.41
     होतात
    0.41
    ▛
    0.41
    élève
    0.41
    Squad
    0.41
    POSITIVE LOGITS
     identifying
    0.53
     prevent
    0.50
     deficient
    0.44
     anticoagulant
    0.43
     timid
    0.42
     perinatal
    0.42
     islets
    0.41
    जनिक
    0.41
     insuffis
    0.41
     inade
    0.41
    Activations Density 0.017%

    No Known Activations