© 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. 86340
    Prev
    Next
    INDEX
    Explanations

    Octopus Discovery license FTP system

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

    tokenization vs words

    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
    🇼
    0.49
    ália
    0.49
    वाड
    0.46
    મિત
    0.46
     kalan
    0.45
    करार
    0.45
    GÁ
    0.45
    acijos
    0.44
    簸
    0.44
    सुबह
    0.43
    POSITIVE LOGITS
     Di
    0.47
     Fle
    0.47
     Card
    0.45
    fen
    0.44
     cargo
    0.43
     Cargo
    0.43
     Bell
    0.42
     Stem
    0.42
     educators
    0.42
     computations
    0.41
    Activations Density 0.001%

    No Known Activations