© 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. 145189
    Prev
    Next
    INDEX
    Explanations

    friends and family

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

    answer =

    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
    avanja
    0.47
     признаки
    0.46
    និង
    0.45
     വാക്ക
    0.45
     सतह
    0.44
    SequentialGroup
    0.44
     영상
    0.44
    鲢
    0.44
     मानसिकता
    0.44
     حصے
    0.43
    POSITIVE LOGITS
     door
    0.45
     open
    0.43
    pool
    0.43
     pool
    0.43
     to
    0.42
     is
    0.41
     free
    0.41
     trusty
    0.40
     easy
    0.39
     gastron
    0.39
    Activations Density 0.000%

    No Known Activations