© 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. 233340
    Prev
    Next
    INDEX
    Explanations

    fictional storytelling myths

    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
    ουν
    0.53
    without
    0.46
    iran
    0.46
    aceous
    0.45
    award
    0.44
    with
    0.44
    োক
    0.44
    忤
    0.44
    religious
    0.43
    cles
    0.43
    POSITIVE LOGITS
     revolving
    0.50
     torno
    0.49
     chat
    0.48
     gim
    0.48
     revolves
    0.48
     campione
    0.47
    =
    0.47
     peers
    0.47
     towers
    0.47
     fragmented
    0.46
    Activations Density 0.000%

    No Known Activations