© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8116
    Prev
    Next
    INDEX
    Explanations

    notes and descriptions

    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
     strikingly
    2.48
     impressively
    2.41
    ВИ
    2.37
     astounding
    2.30
     stunning
    2.24
    笉
    2.23
     amazingly
    2.23
    лу
    2.21
    лаве
    2.19
    <0xA0>
    2.19
    POSITIVE LOGITS
    P
    1.87
    nent
    1.78
    N
    1.74
    I
    1.71
    y
    1.71
    ರ್ಧ
    1.69
    C
    1.68
    en
    1.68
    analog
    1.65
    ﮩ
    1.63
    Activations Density 0.201%

    No Known Activations