© 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. 11281
    Prev
    Next
    INDEX
    Explanations

    slang and cool vibes

    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
     pilgr
    2.88
     numquam
    2.65
    ExpNow
    2.59
    <unused1987>
    2.58
    瞻
    2.57
     Bened
    2.55
    <unused1068>
    2.53
    𒀉
    2.53
    <unused1719>
    2.52
    <unused1854>
    2.51
    POSITIVE LOGITS
    shit
    2.27
    dat
    2.23
    ut
    1.86
    boy
    1.86
    bin
    1.85
    bied
    1.83
    홉
    1.79
     bum
    1.73
    бок
    1.72
    ర్‌
    1.71
    Activations Density 1.192%

    No Known Activations