© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6342
    Prev
    Next
    INDEX
    Explanations

    recipe measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ycled
    0.76
    ikin
    0.74
     менять
    0.73
    amba
    0.67
     ಮೂಲ
    0.65
    сква
    0.65
    rizioni
    0.65
    };//
    0.65
    上がり
    0.64
    angan
    0.63
    POSITIVE LOGITS
    フルーツ
    0.77
     vomiting
    0.72
     глю
    0.71
     esercizi
    0.71
    叶
    0.71
     Artwork
    0.70
     leite
    0.68
     catalase
    0.68
     carrots
    0.68
    atoms
    0.67
    Activations Density 0.017%

    No Known Activations