© 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. 189388
    Prev
    Next
    INDEX
    Explanations

    listing, registration, conversion

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

    list preparation

    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
     :
    0.50
    igs
    0.46
    时
    0.45
    ):
    0.44
     stead
    0.44
    irect
    0.42
     )[
    0.42
    ific
    0.42
    irc
    0.42
     Ra
    0.42
    POSITIVE LOGITS
    Lähteet
    0.50
    Transcription
    0.48
    镕
    0.48
    Prosec
    0.48
     utbild
    0.47
    देखो
    0.46
    کریاں
    0.46
    Kaynakça
    0.46
     våra
    0.45
    ळ्या
    0.43
    Activations Density 0.000%

    No Known Activations