© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15801
    Prev
    Next
    INDEX
    Explanations

    both or either

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.75
     or
    -1.74
     faldas
    -1.51
     huellas
    -1.49
     aguj
    -1.49
     apret
    -1.48
     だっ
    -1.45
     muerta
    -1.43
     sensaciones
    -1.39
     rád
    -1.38
    POSITIVE LOGITS
     are
    2.70
     these
    2.20
     is
    2.00
     of
    1.85
     will
    1.78
    が
    1.53
    は
    1.52
     were
    1.51
     have
    1.50
    を
    1.49
    Activations Density 0.042%

    No Known Activations