© 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. 34-GEMMASCOPE-RES-131K
    7. 45671
    Prev
    Next
    INDEX
    Explanations

    offers, reveals, creates

    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_34/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
     estando
    -1.40
     they
    -1.40
     anklicken
    -1.34
     adecuada
    -1.34
     exclusivamente
    -1.34
     there
    -1.28
     constantemente
    -1.27
     during
    -1.26
     posteriormente
    -1.26
    ductory
    -1.24
    POSITIVE LOGITS
     a
    4.38
     an
    2.33
     something
    1.96
     plenty
    1.73
     enough
    1.66
     another
    1.59
     comentário
    1.53
     μια
    1.49
     not
    1.46
     nothing
    1.41
    Activations Density 0.120%

    No Known Activations