© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1246
    Prev
    Next
    INDEX
    Explanations

    equal to

    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_10/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
    These
    -2.30
     этих
    -1.88
     of
    -1.82
     estos
    -1.80
    a
    -1.69
    r
    -1.67
    Diese
    -1.65
    0
    -1.64
    ON
    -1.63
    un
    -1.61
    POSITIVE LOGITS
     its
    2.30
     the
    2.06
     our
    1.77
     傘
    1.63
     everyone
    1.58
    obscure
    1.55
     podrán
    1.55
     adjoining
    1.54
     localidades
    1.53
     following
    1.52
    Activations Density 0.025%

    No Known Activations