© 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. 11081
    Prev
    Next
    INDEX
    Explanations

    away, washing, bar states

    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
     τ
    1.24
     неболь
    1.21
    ⿲
    1.21
    ставляет
    1.18
     Ша
    1.18
    ≿
    1.18
    ఞ
    1.16
    кол
    1.16
    mathfrak
    1.14
    🦸
    1.13
    POSITIVE LOGITS
    DoS
    0.85
     Rie
    0.82
     potentiel
    0.78
     salvo
    0.78
     potential
    0.76
     weekend
    0.76
     proprio
    0.75
    原始内容存档于
    0.75
     festiv
    0.74
    frist
    0.74
    Activations Density 0.031%

    No Known Activations