© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24144
    Prev
    Next
    INDEX
    Explanations

    promises of virtually limitless

    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
    𝘫
    0.51
     alguna
    0.49
    ಸ್ಕೊ
    0.48
    mex
    0.47
     చేశారు
    0.47
    iyordu
    0.47
    统治
    0.46
     aventuras
    0.46
    orderInCategory
    0.45
    මෙ
    0.44
    POSITIVE LOGITS
     Tesla
    0.53
     ret
    0.50
     not
    0.50
    槎
    0.49
     sé
    0.49
     Prohibition
    0.48
     wil
    0.48
     mince
    0.46
    コス
    0.46
     także
    0.46
    Activations Density 0.000%

    No Known Activations