© 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. 11268
    Prev
    Next
    INDEX
    Explanations

    JavaScript with Obsidian

    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
    𝐞
    1.75
     sdx
    1.67
    𝐚
    1.63
    getIndex
    1.60
    𝐮
    1.60
    irono
    1.59
    ތ
    1.59
    setNome
    1.59
    atsiooni
    1.57
    ieniu
    1.57
    POSITIVE LOGITS
    quera
    1.28
     accepts
    1.19
    y
    1.19
    훅
    1.16
    열
    1.15
     returns
    1.13
     turnovers
    1.13
    나라
    1.10
    κου
    1.10
     acknowledges
    1.09
    Activations Density 0.000%

    No Known Activations