© 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. 161163
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

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

    half-day durations

    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
     πολλ
    0.46
    の上
    0.42
    Backward
    0.41
    ２
    0.40
     постро
    0.40
    Sal
    0.39
    紅
    0.39
     қ
    0.39
    Australia
    0.39
     indes
    0.39
    POSITIVE LOGITS
     Hurricane
    0.48
     গার্ডিয়ান
    0.47
     Structural
    0.46
     preguntas
    0.46
     LLC
    0.46
     Validators
    0.45
     Limestone
    0.45
     guardians
    0.45
     Calhoun
    0.45
     Faith
    0.44
    Activations Density 0.000%

    No Known Activations