© 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. 15407
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by common words

    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
     for
    -2.39
     with
    -1.55
     on
    -1.53
     their
    -1.51
     of
    -1.43
     focusing
    -1.38
     jaja
    -1.36
     adorno
    -1.35
     departament
    -1.30
     preventing
    -1.27
    POSITIVE LOGITS
     molti
    1.61
    訁
    1.60
    ꔹ
    1.55
    iNdEx
    1.52
     Unterscheidung
    1.51
     garantías
    1.47
     fijar
    1.47
    Ꭸ
    1.45
     Auffassung
    1.45
    ámico
    1.44
    Activations Density 0.004%

    No Known Activations