© 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. 170245
    Prev
    Next
    INDEX
    Explanations

    specifically noted, Literally it, defending barrister, Berlin, Facility identified, morning, certification

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

    JSON structures and data handling

    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
     hesitated
    0.57
    olazione
    0.55
     ovviamente
    0.49
     soprattutto
    0.47
     deseja
    0.46
     البته
    0.46
    ل
    0.46
    仕組み
    0.45
    w
    0.45
    ﻟ
    0.45
    POSITIVE LOGITS
     on
    0.46
    мий
    0.43
     dihedral
    0.43
    仲間
    0.42
    щин
    0.42
    TAIN
    0.42
     patterning
    0.42
     conformal
    0.41
    తారు
    0.41
     grievance
    0.41
    Activations Density 0.000%

    No Known Activations