© 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. 7510
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency and code contexts

    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
     …….
    1.02
     ESG
    0.99
    …’
    0.95
     …..
    0.95
     conness
    0.94
     ¼
    0.93
     ….
    0.92
    ….
    0.90
     connected
    0.90
     …
    0.90
    POSITIVE LOGITS
    Advertisement
    1.14
    But
    1.14
    While
    1.13
    AAP
    1.09
    "
    1.07
    Meanwhile
    1.01
    And
    0.89
    Watch
    0.89
    ``
    0.89
    Loading
    0.87
    Activations Density 0.000%

    No Known Activations