© 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. 51009
    Prev
    Next
    INDEX
    Explanations

    numbers and currency symbols

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

    operational status, membership, internal

    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
    রূপে
    0.43
    克
    0.43
    客服
    0.42
    ן
    0.41
    練
    0.41
    نائي
    0.41
    న
    0.41
    રૂ
    0.40
    ria
    0.40
     অর্থাৎ
    0.40
    POSITIVE LOGITS
     PIC
    0.47
     UNI
    0.46
     waivers
    0.46
     랜덤
    0.46
     ска
    0.45
     Waiver
    0.45
     오픈
    0.45
     SPE
    0.45
     обе
    0.45
     Fractal
    0.44
    Activations Density 0.000%

    No Known Activations