© 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. 41-GEMMASCOPE-2-RES-262K
    7. 25188
    Prev
    Next
    INDEX
    Explanations

    concepts, probability, value, water, independent

    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_all/layer_41_width_262k_l0_big
    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
    verw
    0.37
     Windsor
    0.36
     संबोध
    0.36
    btnAdd
    0.36
    žad
    0.36
    鸞
    0.35
    災害
    0.35
    璨
    0.35
     कॉनकॉर्ड
    0.35
     Très
    0.35
    POSITIVE LOGITS
    šen
    0.38
    value
    0.38
     motore
    0.36
    maxValue
    0.36
    щен
    0.35
     barbers
    0.35
     value
    0.35
     lifts
    0.35
     vysok
    0.35
    Possible
    0.34
    Activations Density 0.001%

    No Known Activations