© 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. 148664
    Prev
    Next
    INDEX
    Explanations

    individuales concept

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

    web protocols and browsing

    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
    EEC
    0.50
    kapal
    0.49
    Chan
    0.46
    バリ
    0.45
     fainting
    0.45
    cary
    0.45
    デ
    0.45
    L
    0.44
    Length
    0.44
    Sh
    0.44
    POSITIVE LOGITS
     excelentes
    0.47
     conceitos
    0.46
     individuales
    0.45
     документы
    0.44
    परा
    0.44
     parallels
    0.44
     ergän
    0.44
     undermines
    0.44
     hombres
    0.43
     incluidos
    0.43
    Activations Density 0.000%

    No Known Activations