Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 14458
    Prev
    Next
    INDEX
    Explanations

    range, maintained, survival, accident, CITIC

    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
    .,
    0.45
     completing
    0.44
     +/-
    0.44
    :
    0.43
    led
    0.42
     penny
    0.42
     all
    0.41
     planned
    0.40
     inserted
    0.40
     abl
    0.40
    POSITIVE LOGITS
    亽
    0.53
    ต้องการ
    0.49
     númer
    0.47
    朐
    0.47
    쓱
    0.46
    ır
    0.46
     máscara
    0.46
     Escrit
    0.45
    渴望
    0.45
     numérica
    0.45
    Activations Density 0.001%

    No Known Activations