© 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. 1553
    Prev
    Next
    INDEX
    Explanations

    types of components

    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
     mental
    0.94
     Mental
    0.91
    Mental
    0.81
    0
    0.79
    Social
    0.78
    心理
    0.77
    The
    0.77
     mentale
    0.77
     The
    0.76
    1
    0.74
    POSITIVE LOGITS
     feeders
    1.10
    اونلوډ
    1.08
     versions
    1.01
     inserts
    1.00
     insertions
    0.99
    <unused2131>
    0.99
    ьте
    0.98
     inserting
    0.97
    Sku
    0.96
    дного
    0.95
    Activations Density 0.480%

    No Known Activations