© 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. 55287
    Prev
    Next
    INDEX
    Explanations

    encryption

    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
    ֽ
    0.42
    Ⲩ
    0.41
    ய
    0.40
     സ്വാതന്ത്ര
    0.38
    กา
    0.37
     vele
    0.36
     упраж
    0.36
    ें
    0.36
    ക്കുന്ന
    0.36
    ABET
    0.36
    POSITIVE LOGITS
     floors
    0.44
     sleepers
    0.40
     elastomers
    0.40
    ovu
    0.39
    知道了
    0.38
    坻
    0.38
     oscillators
    0.38
     हरिद्वार
    0.37
    window
    0.37
     sleepy
    0.37
    Activations Density 0.001%

    No Known Activations