© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 39282
    Prev
    Next
    INDEX
    Explanations

    sober, updated, still

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

    estimating, initial, visitors, fund

    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
     നിർ
    0.53
    !
    0.53
    down
    0.45
     emerging
    0.45
    ur
    0.45
     '
    0.43
     安
    0.43
    ss
    0.43
     conference
    0.43
    )
    0.43
    POSITIVE LOGITS
    ArrayBox
    0.53
    าว
    0.50
    FrameLength
    0.50
    MLLoader
    0.49
    嫄
    0.49
    шло
    0.47
    вере
    0.47
    രാജ
    0.47
    膊
    0.47
    斛
    0.47
    Activations Density 0.000%

    No Known Activations