© 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. 12352
    Prev
    Next
    INDEX
    Explanations

    anti- compounds

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

    The hyphen "-" character, particularly in prefixed words like "anti-" where it connects the prefix to the main word.

    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
      
    -2.23
     MUCH
    -2.16
     Anſ
    -2.02
     VERY
    -1.98
    </em>
    -1.97
    氿
    -1.94
     небольшой
    -1.87
     cuja
    -1.86
     sublime
    -1.85
    ⩖
    -1.85
    POSITIVE LOGITS
     passat
    2.13
    While
    2.09
     and
    2.09
     riva
    2.08
     them
    2.03
    ementara
    2.03
    Because
    1.99
    When
    1.98
     being
    1.98
    Like
    1.96
    Activations Density 0.014%

    No Known Activations