© 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. 46232
    Prev
    Next
    INDEX
    Explanations

    annual revenue

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

    causing severePublic Affairsthermal transport

    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
     d
    0.48
     가능하다
    0.48
     pointless
    0.47
     لي
    0.44
     Liam
    0.44
    തും
    0.42
     Д
    0.42
     ငါ
    0.42
     ListItem
    0.41
     hapless
    0.41
    POSITIVE LOGITS
    elsius
    0.49
    URE
    0.44
    новним
    0.43
    uum
    0.43
    উর
    0.43
    INTER
    0.43
    DO
    0.42
    Annual
    0.42
    tere
    0.42
    offset
    0.41
    Activations Density 0.000%

    No Known Activations