© 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. 69609
    Prev
    Next
    INDEX
    Explanations

    newsanalysisarticles

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

    consumers, smell, habitual pitch

    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
    elerde
    0.46
    seit
    0.46
    adel
    0.44
    ̻
    0.43
     العنوان
    0.42
     Gottes
    0.40
    cimentos
    0.40
    বর্তী
    0.40
    vel
    0.40
    лаго
    0.39
    POSITIVE LOGITS
     madam
    0.51
     analyst
    0.47
     ANALYSIS
    0.46
     garner
    0.45
    ণ
    0.45
    っち
    0.44
    ANAL
    0.44
    ದ್ದ
    0.44
     pardon
    0.44
    菸
    0.44
    Activations Density 0.002%

    No Known Activations