© 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. 183884
    Prev
    Next
    INDEX
    Explanations

    December scholarship opportunity

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

    animal shelter, reindeer, groups

    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
    ני
    0.46
    pm
    0.44
    id
    0.44
    은
    0.44
     ತುಂಬಾ
    0.43
    uscany
    0.43
    ตัวเอง
    0.42
    ígeno
    0.42
    raf
    0.41
    คุณ
    0.41
    POSITIVE LOGITS
    ంచరీలు
    0.46
     évaluations
    0.42
    Scores
    0.41
     distribuzione
    0.41
    ᆯ
    0.40
     desempenho
    0.40
    FirstResponder
    0.40
     ghi
    0.39
     dicembre
    0.39
     contraband
    0.39
    Activations Density 0.000%

    No Known Activations