© 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. 165011
    Prev
    Next
    INDEX
    Explanations

    in order to

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

    resin figurines, bar magnets

    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
    Theoretical
    0.52
    冖
    0.50
    hmen
    0.48
    agland
    0.47
    Же
    0.47
    PACK
    0.47
    鄯
    0.47
    illante
    0.47
    Ꭱ
    0.46
    ۰۰
    0.46
    POSITIVE LOGITS
     gunfire
    0.45
     monkey
    0.44
     Derive
    0.44
     derivations
    0.44
     sensors
    0.43
    പൊ
    0.43
     Derek
    0.42
     walnuts
    0.42
     sensory
    0.42
     proactively
    0.42
    Activations Density 0.001%

    No Known Activations