© 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. 36146
    Prev
    Next
    INDEX
    Explanations

    UFusoft pinnacle passage

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

    language descriptions

    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
     tiêu
    0.47
    ất
    0.46
    ặng
    0.46
     °,
    0.46
    ället
    0.44
     s
    0.44
     f
    0.44
     tại
    0.44
     دری
    0.44
     at
    0.43
    POSITIVE LOGITS
    кономі
    0.50
    अनु
    0.49
    zp
    0.49
    রাপ
    0.48
     seznam
    0.47
    registro
    0.47
     largas
    0.47
     inversa
    0.47
    日英
    0.46
    꾹
    0.46
    Activations Density 0.000%

    No Known Activations