© 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. 227402
    Prev
    Next
    INDEX
    Explanations

    free WiFi

    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
     aggregating
    0.49
    を活用
    0.45
    ার্থীর
    0.43
     cytochrome
    0.42
     canh
    0.42
     neurotrans
    0.41
     생
    0.40
     alerts
    0.40
     agrup
    0.40
     showAlert
    0.39
    POSITIVE LOGITS
     Люди
    0.55
    posición
    0.47
     IJ
    0.47
    rotz
    0.47
     люди
    0.46
    gelijk
    0.46
    +:
    0.45
     Preface
    0.44
     Städte
    0.44
    MnO
    0.44
    Activations Density 0.001%

    No Known Activations