© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40461
    Prev
    Next
    INDEX
    Explanations

    day rental fee

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

    punctuation and special characters

    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
     spectroscopic
    0.46
     WINTER
    0.45
    樎
    0.44
     topologies
    0.43
     겨울
    0.42
     Schwarzschild
    0.42
     synchrotron
    0.40
     torsional
    0.40
    隰
    0.40
    :</
    0.40
    POSITIVE LOGITS
     violently
    0.47
    érie
    0.45
    ări
    0.45
    ation
    0.43
    ată
    0.41
    iqui
    0.41
    કરી
    0.41
     almighty
    0.41
    iza
    0.40
     तरीके
    0.40
    Activations Density 0.000%

    No Known Activations