© 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. 7439
    Prev
    Next
    INDEX
    Explanations

    distinct actions or states

    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
    ត្រូវបាន
    0.53
     casser
    0.48
     szüks
    0.45
     erwäh
    0.45
    蛰
    0.45
     éviter
    0.45
     टाटा
    0.45
     cappuccino
    0.45
     relatifs
    0.45
    តែ
    0.44
    POSITIVE LOGITS
    x
    0.46
     Langkah
    0.44
    CONSTRAINT
    0.44
     Dependence
    0.40
    ב
    0.40
    q
    0.39
    전
    0.39
    h
    0.39
    cm
    0.39
    INTEGER
    0.38
    Activations Density 0.009%

    No Known Activations