© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8262
    Prev
    Next
    INDEX
    Explanations

    percentages and formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     வால்பேப்பர்
    1.08
    <unused790>
    1.08
    Estamos
    1.07
     glTexParameteri
    1.06
    伖
    1.06
     வண்ணப்பூச்சு
    1.05
    ୯
    1.05
    肆章
    1.04
    伨
    1.04
    પે
    1.03
    POSITIVE LOGITS
     high
    0.72
     special
    0.67
     get
    0.65
     keeping
    0.65
     prec
    0.64
     all
    0.64
     independent
    0.63
     some
    0.63
    高
    0.62
     max
    0.61
    Activations Density 0.001%

    No Known Activations