© 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. 201619
    Prev
    Next
    INDEX
    Explanations

    warning signs

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

    objects, skills, anatomy, orientation, gate

    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
    ו
    0.55
    дар
    0.52
    та
    0.51
     estabele
    0.48
     peraturan
    0.46
    дары
    0.45
    स्ट्रेट
    0.45
    薈
    0.45
    場で
    0.44
    دە
    0.44
    POSITIVE LOGITS
    icolored
    0.53
    Install
    0.52
    Dumper
    0.52
    Dump
    0.51
     Gazetteer
    0.50
     Industrial
    0.50
     Realtors
    0.50
     Reap
    0.50
     Brooklyn
    0.49
    having
    0.49
    Activations Density 0.001%

    No Known Activations