© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13178
    Prev
    Next
    INDEX
    Explanations

    digits or price

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
     shown
    0.59
     losses
    0.56
    IONAL
    0.55
     gitu
    0.54
     forwarding
    0.53
     Aussch
    0.53
     stored
    0.53
    <()>
    0.53
     syscall
    0.52
     submits
    0.52
    POSITIVE LOGITS
    㽚
    0.59
    侢
    0.57
    agia
    0.57
     мә
    0.55
    twig
    0.55
    㤟
    0.55
     кро
    0.55
     renewable
    0.54
    pia
    0.54
    韵
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.