© 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. 42005
    Prev
    Next
    INDEX
    Explanations

    names dated workshop paper

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

    does think, cannot understand

    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
     recounted
    0.55
    枸
    0.52
     д
    0.52
     coincided
    0.50
    ।”
    0.49
    𝒅
    0.49
     doves
    0.49
    ovll
    0.48
     рођено
    0.48
    '`--'`--
    0.48
    POSITIVE LOGITS
    (
    0.56
    Associ
    0.44
    Layout
    0.43
    นัก
    0.43
    Creative
    0.42
    식을
    0.42
    R
    0.42
    Kind
    0.42
    S
    0.42
    Image
    0.41
    Activations Density 0.000%

    No Known Activations