© 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. 145398
    Prev
    Next
    INDEX
    Explanations

    saying "Time is a terrible thing

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

    programming language concepts

    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
     représentation
    0.50
     realising
    0.49
    ᓯ
    0.45
     waking
    0.44
    奨
    0.43
     Vegas
    0.43
     yakin
    0.42
     négoci
    0.42
    াস্থ্যের
    0.42
     helium
    0.41
    POSITIVE LOGITS
    OF
    0.48
     }%
    0.47
    pf
    0.46
    omeric
    0.46
    ')(
    0.46
    IC
    0.46
     %=
    0.45
    先把
    0.45
    Ancestor
    0.45
     Primitive
    0.44
    Activations Density 0.000%

    No Known Activations