© 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. 52660
    Prev
    Next
    INDEX
    Explanations

    mask and eyes

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

    masks and mandates

    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
     рее
    0.47
    LAUNCH
    0.46
    Rez
    0.44
    GUID
    0.43
    ревно
    0.42
     талант
    0.42
    KeyEvent
    0.42
    奖
    0.41
    ictions
    0.41
    bursements
    0.40
    POSITIVE LOGITS
     mask
    1.25
     masks
    1.20
     máscara
    1.16
     Mask
    1.14
     Masks
    1.12
    マスク
    1.09
     masker
    1.09
    mask
    1.05
     másc
    1.04
    Mask
    1.02
    Activations Density 0.025%

    No Known Activations