© 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. 138611
    Prev
    Next
    INDEX
    Explanations

    eager growth manager employment

    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
    гас
    0.45
     kilomètres
    0.44
     chrét
    0.44
     hạnh
    0.44
    нося
    0.43
     adquir
    0.43
    Happiness
    0.43
     通
    0.42
     langues
    0.42
    RequestMethod
    0.42
    POSITIVE LOGITS
    Peach
    0.47
    inen
    0.46
    Puerto
    0.45
    𝟐
    0.45
    innen
    0.45
    ther
    0.44
     உயிர்
    0.44
    osphate
    0.44
    าะ
    0.44
    ⚓
    0.42
    Activations Density 0.003%

    No Known Activations