© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2441
    Prev
    Next
    INDEX
    Explanations

    requests for ten items

    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_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
    మ
    0.85
    trimenti
    0.77
     Attacks
    0.76
     Donations
    0.76
     αρ
    0.74
     Contributions
    0.74
     Attack
    0.72
     Contribution
    0.71
     ம
    0.71
     Allowed
    0.70
    POSITIVE LOGITS
     perspekt
    0.80
    perspective
    0.78
    todo
    0.77
     dozen
    0.74
     prototyp
    0.73
    giraffe
    0.72
    enediamine
    0.70
     बाहेर
    0.69
    7
    0.69
    หาย
    0.69
    Activations Density 0.138%

    No Known Activations