© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25356
    Prev
    Next
    INDEX
    Explanations

    of these; these of

    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
     after
    -1.09
     or
    -0.98
     from
    -0.96
     with
    -0.95
     time
    -0.88
     out
    -0.86
     during
    -0.85
    両方
    -0.81
     as
    -0.80
    solution
    -0.80
    POSITIVE LOGITS
    を目指す
    0.95
     vérification
    0.94
     Füße
    0.92
     Chancen
    0.90
    Anche
    0.90
     Nachteile
    0.89
     coroa
    0.88
    ₆
    0.88
     território
    0.88
     piring
    0.88
    Activations Density 0.128%

    No Known Activations