© 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. 5609
    Prev
    Next
    INDEX
    Explanations

    light, Compress

    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
    팎
    1.19
     তবু
    1.17
    asText
    1.11
    прочем
    1.10
    சரி
    1.08
     ugly
    1.03
    没人
    1.03
    reszt
    1.02
    ugly
    1.00
    ].)
    1.00
    POSITIVE LOGITS
     utilizando
    1.73
     utilizzando
    1.61
     utilising
    1.46
     utilizing
    1.45
     بتاريخ
    1.42
     Utilizing
    1.38
     дан
    1.36
     aşağıdaki
    1.35
     باستخدام
    1.35
     conformément
    1.35
    Activations Density 0.112%

    No Known Activations