Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 1364
    Prev
    Next
    INDEX
    Explanations

    big-picture behavior

    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_16k_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
    -
    1.40
    L
    1.07
    it
    0.99
    H
    0.95
    xi
    0.91
    And
    0.89
    pace
    0.88
    S
    0.88
    number
    0.88
    Nov
    0.88
    POSITIVE LOGITS
     considerations
    1.06
     iterative
    1.04
     racism
    1.03
     collaborative
    1.03
     libertarian
    1.02
     autocratic
    1.01
     authoritarian
    1.01
     cheeky
    1.01
     customizable
    1.00
     hypocrisy
    1.00
    Activations Density 0.579%

    No Known Activations