© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59011
    Prev
    Next
    INDEX
    Explanations

    Negotiating and control of

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

    the presence of non-alphanumeric symbols and punctuation (especially single quotes and similar marks)

    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
     Saltar
    -2.16
    鎹
    -2.05
    閹
    -1.91
     yaşında
    -1.81
    pośred
    -1.81
    arakhand
    -1.80
     sebagai
    -1.78
    蒟
    -1.77
    為了
    -1.77
    éni
    -1.75
    POSITIVE LOGITS
    ."
    2.64
     "
    2.63
    ↵
    2.27
    u
    2.25
    L
    2.22
    or
    2.20
    of
    2.20
    h
    2.19
    en
    2.17
     of
    2.17
    Activations Density 0.020%

    No Known Activations