© 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. 22-GEMMASCOPE-RES-131K
    7. 39472
    Prev
    Next
    INDEX
    Explanations

    introducing a point

    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
     also
    -1.42
     they
    -1.42
     também
    -1.34
    also
    -1.33
     также
    -1.18
     zdar
    -1.10
     nowy
    -1.09
     également
    -1.09
    urr
    -1.05
     universitarios
    -1.05
    POSITIVE LOGITS
     haphazard
    1.19
     supremely
    1.16
     ostensibly
    1.16
     Obviously
    1.16
     overtly
    1.15
     radically
    1.13
     незавер
    1.13
     innumerable
    1.12
     potencial
    1.12
     wholly
    1.12
    Activations Density 0.034%

    No Known Activations