© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101097
    Prev
    Next
    INDEX
    Explanations

    again until

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

    the adverb “again,” i.e. explicit mentions of repeated action.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    }$
    -2.08
     другую
    -1.70
    	
    -1.70
    et
    -1.67
     ciertas
    -1.66
    }
    -1.60
    But
    -1.57
    覬
    -1.57
    Berikut
    -1.54
     devem
    -1.53
    POSITIVE LOGITS
     of
    2.38
     for
    2.03
    ."
    1.73
     in
    1.63
    СТО
    1.57
     najdete
    1.54
    ции
    1.54
     from
    1.52
    []{"
    1.52
    mybatisplus
    1.49
    Activations Density 0.003%

    No Known Activations