© 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. 189068
    Prev
    Next
    INDEX
    Explanations

    problems or future events

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

    testing frameworks and reporting practices

    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
     นอกจาก
    0.42
    हरियाणा
    0.42
     ',');
    0.41
     stej
    0.41
     گزشتہ
    0.41
    getSaveLocation
    0.41
     twisting
    0.40
    那我們
    0.40
    男生
    0.39
     सबकी
    0.39
    POSITIVE LOGITS
    i
    0.55
    wave
    0.50
    live
    0.50
    iin
    0.50
    ი
    0.48
    h
    0.47
    incorporated
    0.47
    combat
    0.47
    sulf
    0.46
    called
    0.46
    Activations Density 0.000%

    No Known Activations