© 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. 105048
    Prev
    Next
    INDEX
    Explanations

    tbl followed by table names

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

    the token "tbl" (typically used as an abbreviation for "table" in database contexts).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    a
    -3.28
    𝕖
    -3.05
    饹
    -2.78
    
    -2.66
    撂
    -2.56
    𓄹
    -2.48
    ↵
    -2.42
     focuses
    -2.42
     که
    -2.39
    );
    -2.38
    POSITIVE LOGITS
    when
    2.64
    釓
    2.50
     theoretically
    2.41
    (
    2.39
     straightforward
    2.34
    镡
    2.33
     If
    2.31
     cumbersome
    2.31
    because
    2.30
     utilizzati
    2.30
    Activations Density 0.002%

    No Known Activations