© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141245
    Prev
    Next
    INDEX
    Explanations

    private information

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

    capabilities, trace, IQ, May, sysctl

    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
    Negative Logits
    kl
    0.58
    ِ
    0.56
    pip
    0.51
    am
    0.49
    de
    0.48
    }},
    0.48
    re
    0.46
     of
    0.46
    pr
    0.46
    ags
    0.45
    POSITIVE LOGITS
     newfound
    0.57
    tpVar
    0.54
    ፅ
    0.48
     dilation
    0.46
     uttering
    0.46
     driveway
    0.45
     counsellor
    0.45
     ውሃ
    0.45
    ﻪ
    0.45
    𒉌
    0.45
    Activations Density 0.001%

    No Known Activations