© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 418
    Prev
    Next
    INDEX
    Explanations

    at its core

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     types
    1.38
    こと
    1.31
    ei
    1.27
    e
    1.16
     arrond
    1.16
     type
    1.08
    child
    1.08
     TYPES
    1.06
    ه
    1.06
     pièces
    1.04
    POSITIVE LOGITS
     least
    2.44
     Least
    1.99
    least
    1.73
    Least
    1.57
     behest
    1.47
     forefront
    1.39
     expense
    1.38
    PropertySheets
    1.36
    atürk
    1.35
     halftime
    1.35
    Activations Density 0.377%

    No Known Activations