© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198475
    Prev
    Next
    INDEX
    Explanations

    intended

    np_acts-logits-general · gemini-2.5-flash-lite

    targeted outcomes and research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﻷ
    0.50
    বড়
    0.49
     обслу
    0.48
    賊
    0.48
     consequências
    0.47
    俥
    0.47
    \})
    0.46
     근무
    0.46
    ডো
    0.46
    勂
    0.46
    POSITIVE LOGITS
     ____________
    0.53
     __________
    0.51
    as
    0.51
     .
    0.49
     _____________
    0.48
     ____
    0.48
     _____
    0.48
     ______
    0.47
    WI
    0.46
     RU
    0.46
    Activations Density 0.000%

    No Known Activations