© 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. 76951
    Prev
    Next
    INDEX
    Explanations

    measure loss prayer terminals generation tickets

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

    evolution not a ladder

    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
     따로
    0.54
     xhrObj
    0.47
     రోజు
    0.45
    成立于
    0.44
     때문에
    0.44
     (&
    0.44
     inimes
    0.44
    为大家
    0.43
    ค่อย
    0.43
     Tatra
    0.42
    POSITIVE LOGITS
    ständen
    0.53
    h
    0.51
    wins
    0.50
     số
    0.47
    scales
    0.46
    evaluated
    0.45
    node
    0.44
    grond
    0.44
    c
    0.44
    ре
    0.44
    Activations Density 0.001%

    No Known Activations