© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1198
    Prev
    Next
    INDEX
    Explanations

    turn on, turn off, turn key, turn server

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

    the word "turn" or "Turn" (especially at the beginning of a phrase or title).

    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
    0
    -3.27
    Ἢ
    -2.48
    葙
    -2.34
     pertumbuhan
    -2.31
    賔
    -2.27
    祘
    -2.23
    っぱり
    -2.23
     ткани
    -2.11
    鱟
    -2.11
    かっ
    -2.09
    POSITIVE LOGITS
    .’
    2.98
     nią
    2.86
     them
    2.83
     trouvez
    2.58
     nebst
    2.55
    The
    2.53
    şört
    2.47
     Städten
    2.44
     Briefe
    2.41
    ].
    2.36
    Activations Density 0.020%

    No Known Activations