© 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. 228247
    Prev
    Next
    INDEX
    Explanations

    assurance, probability, eligibility

    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
    smöglichkeiten
    0.48
     Trên
    0.47
    稞
    0.47
    給大家
    0.46
     動物
    0.46
     ตาย
    0.46
     Když
    0.46
    ऑन
    0.45
     entsprechende
    0.45
    ણો
    0.44
    POSITIVE LOGITS
    atz
    0.46
     metodología
    0.45
    OF
    0.45
    h
    0.43
    FRAME
    0.43
    ofs
    0.43
     paradoxical
    0.43
    ிய
    0.42
     compensatory
    0.42
    Freeman
    0.42
    Activations Density 0.001%

    No Known Activations