© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 50943
    Prev
    Next
    INDEX
    Explanations

    structure or state

    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
    s
    0.65
     maio
    0.54
    más
    0.52
     suspe
    0.52
     socialista
    0.48
     convivial
    0.47
     scarcely
    0.46
     conviv
    0.45
     más
    0.45
     well
    0.45
    POSITIVE LOGITS
    ้น
    0.46
    ଂ
    0.46
    댓글
    0.45
    比如說
    0.44
    KOM
    0.43
     indiquer
    0.42
    োহণ
    0.42
    简
    0.42
    酶
    0.41
     intercepts
    0.41
    Activations Density 0.000%

    No Known Activations