© 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. 22-GEMMASCOPE-2-RES-262K
    7. 11543
    Prev
    Next
    INDEX
    Explanations

    temperatures or code examples

    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
    ఘ
    0.64
    টাকে
    0.61
     człon
    0.60
     это
    0.60
    lanelet
    0.59
     wegen
    0.58
    Loss
    0.58
    それが
    0.58
    は約
    0.57
    它是
    0.57
    POSITIVE LOGITS
    ั่ว
    0.75
    ಬ್ಬ
    0.69
    сії
    0.64
    कोर
    0.63
    Œ
    0.62
    applicant
    0.62
    calibration
    0.61
    viu
    0.61
     মূ
    0.60
     عر
    0.60
    Activations Density 0.002%

    No Known Activations