© 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. 13737
    Prev
    Next
    INDEX
    Explanations

    split into parts

    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
    ،
    1.55
     وم
    1.49
    ,
    1.48
    ل
    1.34
    and
    1.32
     and
    1.28
    และ
    1.27
    .
    1.26
    ميم
    1.25
    :
    1.24
    POSITIVE LOGITS
     cenário
    1.57
     giochi
    1.54
     peru
    1.45
     vendredi
    1.45
     duelo
    1.44
     domani
    1.44
     therap
    1.44
     confronto
    1.43
     prossima
    1.43
     conferencia
    1.43
    Activations Density 0.000%

    No Known Activations