© 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. 14525
    Prev
    Next
    INDEX
    Explanations

    a specific item or concept

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

    Boromir, these, this scenario

    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
    g
    0.55
    z
    0.51
    rags
    0.47
    قبال
    0.46
    dade
    0.45
    amiento
    0.45
    sett
    0.45
     mismanagement
    0.45
     manifestations
    0.45
     huv
    0.44
    POSITIVE LOGITS
    沺
    0.47
    柽
    0.45
    瑩
    0.44
    את
    0.44
    晨
    0.44
    или
    0.44
    骢
    0.43
    OTA
    0.43
    ЕР
    0.43
    АО
    0.43
    Activations Density 0.000%

    No Known Activations