© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2899
    Prev
    Next
    INDEX
    Explanations

    denominations (quarters, dimes, nickels, pennies)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ግን
    0.31
    などに
    0.31
     Расійскай
    0.31
     derivada
    0.30
    ZrO
    0.29
     LMFBR
    0.29
    🇴
    0.29
     MEX
    0.28
     Renderer
    0.27
    <0x97>
    0.27
    POSITIVE LOGITS
     respectiv
    0.36
    हून
    0.32
     entrambi
    0.32
     ambos
    0.31
     ذریع
    0.31
    .}$
    0.30
     unul
    0.30
     tarafından
    0.30
     entrambe
    0.29
    ग्राह
    0.29
    Activations Density 0.685%

    No Known Activations