© 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. 233497
    Prev
    Next
    INDEX
    Explanations

    parcours also chosen grave

    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
    乎
    0.49
    Smooth
    0.47
    (.*
    0.47
     제주
    0.47
     рей
    0.46
    ranno
    0.46
    kde
    0.46
    সো
    0.45
    smooth
    0.44
    ٸ
    0.44
    POSITIVE LOGITS
    cheon
    0.45
    ក៏
    0.44
    illes
    0.44
     parcours
    0.43
    iquement
    0.42
    ole
    0.42
     Rond
    0.42
    rit
    0.42
     fois
    0.42
    olle
    0.42
    Activations Density 0.000%

    No Known Activations