© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7935
    Prev
    Next
    INDEX
    Explanations

    number of countable things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    色々
    1.94
     المالية
    1.81
    雰
    1.76
    áculos
    1.75
    modo
    1.72
     المختلفة
    1.71
     principaux
    1.70
    ranges
    1.68
    curities
    1.66
     مختلفة
    1.65
    POSITIVE LOGITS
    ⓘ
    1.83
    citation
    1.74
     detections
    1.72
     repeat
    1.69
     reported
    1.67
     complaint
    1.67
    occurrence
    1.66
     successful
    1.65
     takers
    1.59
     unreported
    1.53
    Activations Density 0.172%

    No Known Activations