© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3336
    Prev
    Next
    INDEX
    Explanations

    App instantiation or declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    מ
    0.66
    ר
    0.60
    ка
    0.59
    ки
    0.58
     нажа
    0.58
    Datei
    0.58
    dropbox
    0.57
     user
    0.56
    如果是
    0.56
    если
    0.56
    POSITIVE LOGITS
     Einige
    0.72
    .}$
    0.68
     Beberapa
    0.65
     Welding
    0.64
     Rhys
    0.64
     Burb
    0.64
    Wales
    0.64
     Workshops
    0.63
     Vass
    0.63
     🥰
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.