© 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. 4328
    Prev
    Next
    INDEX
    Explanations

    lists of ways

    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
    دى
    0.45
     tendremos
    0.44
    ча
    0.44
    נס
    0.43
     lymphoblastic
    0.43
    िर
    0.43
    יל
    0.43
    ᾗ
    0.43
    щего
    0.42
     millennium
    0.42
    POSITIVE LOGITS
     उक्त
    0.43
     தொடர்ந்து
    0.40
     செய்தனர்
    0.38
    aje
    0.37
     தெரிவித்த
    0.37
    通信
    0.36
     Alpha
    0.36
     Beta
    0.36
    —”
    0.35
    kc
    0.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.