© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 187826
    Prev
    Next
    INDEX
    Explanations

    without cheat or modifications

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

    identifying lists or explanations

    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
     Geschwindigkeit
    0.52
    m
    0.50
    tr
    0.49
     sinds
    0.47
     Wunsch
    0.46
     Bes
    0.46
     Voll
    0.46
    rd
    0.46
     Rahmen
    0.46
     bes
    0.46
    POSITIVE LOGITS
    Emails
    0.51
    하십시오
    0.48
    ণের
    0.48
     освіти
    0.47
    ledu
    0.46
    各类
    0.46
    各
    0.46
    诙
    0.46
    ຄວາມ
    0.46
    部队
    0.46
    Activations Density 0.000%

    No Known Activations