© 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. 113639
    Prev
    Next
    INDEX
    Explanations

    between entities

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

    distinguishing from speculation

    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
     haf
    0.51
     numai
    0.50
    ’
    0.49
     soğ
    0.49
     raíz
    0.47
     còn
    0.47
    த்தில்
    0.46
    ς
    0.45
     psicol
    0.45
     apresenta
    0.45
    POSITIVE LOGITS
     পায়ের
    0.48
    Stop
    0.46
     "--
    0.45
     crucifixion
    0.45
     ",
    0.43
    STOP
    0.42
     পায়ের
    0.42
     rostrum
    0.41
    --
    0.41
    ottam
    0.41
    Activations Density 0.000%

    No Known Activations