© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90984
    Prev
    Next
    INDEX
    Explanations

    history, culture, physics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    </b>
    0.43
     imitated
    0.40
     срав
    0.39
    ↵
    0.39
     uncles
    0.37
     органов
    0.37
     서
    0.36
    யம்
    0.36
    she
    0.36
     कही
    0.36
    POSITIVE LOGITS
    ঞ্জাম
    0.53
    ڄ
    0.50
    emitter
    0.47
    atisf
    0.47
    ijt
    0.47
     destra
    0.46
    ٹا
    0.46
    ણામ
    0.46
    ledovatel
    0.44
    煐
    0.44
    Activations Density 0.004%

    No Known Activations