© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1252
    Prev
    Next
    INDEX
    Explanations

    years of experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     COMPLET
    0.98
     Aleks
    0.94
     Роб
    0.94
    pok
    0.88
     complet
    0.87
     Fabi
    0.86
     TOT
    0.85
    º
    0.85
    полу
    0.85
    nikov
    0.84
    POSITIVE LOGITS
     परिवारों
    0.99
     familles
    0.90
    이며
    0.89
     කර
    0.86
     แต่
    0.85
     familias
    0.83
     stringWith
    0.83
     용
    0.82
     vùng
    0.82
     families
    0.82
    Activations Density 0.053%

    No Known Activations