© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72123
    Prev
    Next
    INDEX
    Explanations

    counting occurrences and scores

    np_acts-logits-general · gemini-2.5-flash-lite

    counting occurrences and scores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     বৃহত্তম
    0.51
     CALCUL
    0.49
    ûr
    0.42
    徳
    0.42
    Ricardo
    0.41
     積
    0.41
     Largest
    0.41
    earch
    0.40
    ді
    0.40
    mg
    0.40
    POSITIVE LOGITS
    ناد
    0.49
     count
    0.48
    횟
    0.47
     تعداد
    0.47
    갯
    0.46
     ocurr
    0.46
     erud
    0.46
     incidences
    0.46
     psychiat
    0.45
     triunfo
    0.45
    Activations Density 0.002%

    No Known Activations