© 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. 91577
    Prev
    Next
    INDEX
    Explanations

    controls the flow

    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
    愉快
    0.46
    मध
    0.45
     Least
    0.44
    栦
    0.44
    mě
    0.43
    νή
    0.43
    运动
    0.42
    现代
    0.42
    म
    0.42
    我对
    0.41
    POSITIVE LOGITS
    :
    0.64
     emerges
    0.48
    duc
    0.47
    ]
    0.46
    fand
    0.45
     appropri
    0.45
    ?
    0.45
     can
    0.45
     allongé
    0.44
     wearables
    0.43
    Activations Density 0.001%

    No Known Activations