© 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. 95182
    Prev
    Next
    INDEX
    Explanations

    daily micro-management

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

    specific nouns and entities

    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
    inti
    0.48
    ician
    0.48
    yaratan
    0.47
    砜
    0.47
     contaminación
    0.45
     СМИ
    0.43
     COE
    0.42
     એવી
    0.42
    屉
    0.42
    𝔾
    0.42
    POSITIVE LOGITS
     Wasn
    0.54
     jours
    0.49
    Stretch
    0.46
    時間に
    0.45
     wasn
    0.45
     twierd
    0.45
     getView
    0.44
    נים
    0.44
     slouch
    0.43
     czasie
    0.42
    Activations Density 0.000%

    No Known Activations