© 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. 17956
    Prev
    Next
    INDEX
    Explanations

    viewport description

    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
    h
    0.55
    v
    0.51
    very
    0.47
    Two
    0.47
    Sh
    0.47
    b
    0.46
    osts
    0.46
    :
    0.45
    es
    0.45
    Trans
    0.45
    POSITIVE LOGITS
     amacı
    0.48
     auteur
    0.44
     describir
    0.44
     adrenergic
    0.43
     asignatura
    0.43
     turbidity
    0.43
     dirigente
    0.42
    водитель
    0.42
     salicylate
    0.42
     "?"]
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.