© 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. 216824
    Prev
    Next
    INDEX
    Explanations

    guides and resources for millions

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

    point or shot

    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
    鑾
    0.47
     CREE
    0.43
    RAMM
    0.42
     mols
    0.42
     muons
    0.42
     kucing
    0.41
     acidified
    0.41
     VER
    0.41
     clamps
    0.41
     clamping
    0.41
    POSITIVE LOGITS
     pérdida
    0.49
     그냥
    0.48
    There
    0.46
    वर्तमान
    0.46
     affectionate
    0.46
    점
    0.46
    cohol
    0.46
     അവരുടെ
    0.46
     потеря
    0.46
     пережи
    0.46
    Activations Density 0.001%

    No Known Activations