© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 35783
    Prev
    Next
    INDEX
    Explanations

    flash fiction about stories

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ாக
    1.30
    س
    1.09
    ek
    1.04
    ет
    0.98
     to
    0.90
    ish
    0.90
    okban
    0.90
    ete
    0.89
    ches
    0.86
    dio
    0.85
    POSITIVE LOGITS
    l
    1.20
    ר
    1.20
    </td>
    1.19
    </strong>
    1.16
    ;
    1.13
    ﻲ
    1.09
    <0x0D>
    1.08
    μα
    1.06
    C
    1.06
    </b>
    1.04
    Activations Density 0.004%

    No Known Activations