© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127581
    Prev
    Next
    INDEX
    Explanations

    SPECT study

    np_acts-logits-general · gemini-2.5-flash-lite

    conditional statements in programming code, particularly patterns where a condition is followed by a block.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     حتی
    -1.55
     favoriser
    -1.41
    even
    -1.38
     gier
    -1.37
     flink
    -1.35
     даже
    -1.30
     lokale
    -1.28
     annen
    -1.27
    镲
    -1.27
    currently
    -1.25
    POSITIVE LOGITS
     this
    1.81
     for
    1.80
     because
    1.68
     after
    1.63
     from
    1.61
     when
    1.60
     should
    1.60
     a
    1.58
     that
    1.49
     in
    1.40
    Activations Density 0.009%

    No Known Activations