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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1410
    Prev
    Next
    INDEX
    Explanations

    text HOME to 741741

    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_29_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
    cings
    0.71
    ulum
    0.69
    ประ
    0.69
    świę
    0.68
     recieved
    0.68
    ྙ
    0.67
    leman
    0.66
     solen
    0.66
     CONDUCT
    0.64
     Sel
    0.64
    POSITIVE LOGITS
    rn
    0.59
    তায়
    0.52
    usin
    0.50
    eno
    0.50
    种
    0.49
    No
    0.49
     mode
    0.49
     virtual
    0.49
    तों
    0.49
     pemain
    0.48
    Activations Density 0.182%

    No Known Activations