© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1784
    Prev
    Next
    INDEX
    Explanations

    data schema definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    D
    0.71
    break
    0.68
     intensified
    0.68
    ach
    0.66
    gate
    0.65
    strate
    0.62
     land
    0.62
    d
    0.62
     plough
    0.61
    land
    0.61
    POSITIVE LOGITS
     nullable
    1.42
    nullable
    1.28
     obligatorio
    1.12
    Nonnull
    1.10
     descricao
    1.04
    Nullable
    1.04
    可选
    1.00
     readonly
    0.99
     descrizione
    0.98
     Optional
    0.95
    Activations Density 0.192%

    No Known Activations