© 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. 67394
    Prev
    Next
    INDEX
    Explanations

    EchoEndpoint

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

    some other languages

    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
    ifying
    0.46
    ifier
    0.44
    ्यास
    0.42
    tear
    0.42
    endum
    0.41
    ust
    0.40
    どちら
    0.40
    ク
    0.40
    跇
    0.40
    ifie
    0.40
    POSITIVE LOGITS
     zašt
    0.51
     speculate
    0.47
     современных
    0.47
     dibangun
    0.47
     moderne
    0.47
     presume
    0.47
     seorang
    0.46
     décrit
    0.46
     nějak
    0.46
     برخی
    0.45
    Activations Density 0.000%

    No Known Activations