© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3756
    Prev
    Next
    INDEX
    Explanations

    if applicable or hypothetical situations

    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
     ought
    0.73
    hanahu
    0.72
    🕉
    0.68
    〽
    0.68
    <unused2158>
    0.67
    ☇
    0.67
     zouden
    0.67
    🤲
    0.66
    🤛
    0.66
     необходимые
    0.65
    POSITIVE LOGITS
     enjoying
    1.25
     applicable
    1.04
     using
    1.04
     taking
    1.02
     aiming
    1.01
     pursuing
    1.00
     participating
    0.97
     applying
    0.94
     doing
    0.94
     experiencing
    0.93
    Activations Density 0.036%

    No Known Activations