© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30184
    Prev
    Next
    INDEX
    Explanations

    code is

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

    The neuron flags boilerplate copyright and license header text (e.g., “All rights reserved,” “Use of this source code is governed by a BSD‐style license,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getDay
    -0.71
    陳
    -0.70
     Day
    -0.68
     worsened
    -0.68
     tenancy
    -0.68
     Aufg
    -0.67
     prints
    -0.66
    حي
    -0.66
     pays
    -0.65
     print
    -0.64
    POSITIVE LOGITS
    짤
    0.71
     consolidated
    0.69
     COMPETITION
    0.68
    edges
    0.67
     footnotes
    0.67
    assung
    0.65
     compacta
    0.65
    boh
    0.64
     pung
    0.64
    ilage
    0.63
    Activations Density 0.131%

    No Known Activations