© 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. 3483
    Prev
    Next
    INDEX
    Explanations

    examples

    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
    assertEqual
    0.65
    gara
    0.65
    yı
    0.65
    KeyPair
    0.63
    იკ
    0.63
    Ṛ
    0.62
     Atau
    0.61
    }),
    0.60
    ască
    0.60
    UIColor
    0.59
    POSITIVE LOGITS
     Facebook
    0.65
     establecida
    0.65
     funded
    0.63
     blogging
    0.63
     facebook
    0.62
     Fellowship
    0.61
     paso
    0.61
     gracias
    0.60
     adolescent
    0.60
     disminuir
    0.60
    Activations Density 0.113%

    No Known Activations