© 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. 234707
    Prev
    Next
    INDEX
    Explanations

    blacklisted status

    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
    ofile
    0.44
    UP
    0.43
    unet
    0.43
    و
    0.42
    );
    0.42
    </h5>
    0.41
    替代
    0.41
    ot
    0.41
    untz
    0.40
    osti
    0.40
    POSITIVE LOGITS
     perturbations
    0.59
    요일
    0.51
     mesons
    0.51
     conund
    0.50
     enormes
    0.50
     relentless
    0.49
     vérit
    0.49
     whispers
    0.48
    テンツ
    0.48
     craziness
    0.47
    Activations Density 0.001%

    No Known Activations