© 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. 70056
    Prev
    Next
    INDEX
    Explanations

    leather wheel

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

    end of sentence "This"

    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
    BTN
    0.51
    赠
    0.49
    츈
    0.49
    يل
    0.49
    мся
    0.49
     அனைத்து
    0.48
     przypad
    0.48
    贈
    0.48
    UMI
    0.48
    പ്പോ
    0.47
    POSITIVE LOGITS
    </u>
    0.45
     Peter
    0.45
     orchestras
    0.44
    ibility
    0.43
    ability
    0.42
    husband
    0.42
     fo
    0.42
     classifiers
    0.41
    v
    0.41
    land
    0.40
    Activations Density 0.001%

    No Known Activations