© 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. 118447
    Prev
    Next
    INDEX
    Explanations

    answers and explanations

    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
     a
    -1.26
    maining
    -1.14
     this
    -1.14
     növény
    -1.13
     لهذه
    -1.10
    /</
    -1.07
    timmung
    -1.06
    bility
    -1.06
    aried
    -1.06
    iteration
    -1.05
    POSITIVE LOGITS
     they
    2.33
     I
    1.83
     haven
    1.74
     you
    1.73
     might
    1.71
     hasn
    1.67
     wasn
    1.66
     check
    1.63
     there
    1.59
     isn
    1.59
    Activations Density 0.086%

    No Known Activations