© 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. 104381
    Prev
    Next
    INDEX
    Explanations

    take control of

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

    the phrase "control of" in contexts involving authority, power, or possession.

    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
    t
    -1.91
    <i>
    -1.58
    </i>
    -1.52
    you
    -1.41
    return
    -1.37
     avid
    -1.35
     jeśli
    -1.34
     —
    -1.33
    a
    -1.32
    <strong>
    -1.30
    POSITIVE LOGITS
    prende
    1.98
    tividade
    1.97
    prender
    1.88
    licante
    1.73
    cún
    1.65
    şağı
    1.64
    ógicos
    1.63
    gencias
    1.61
    sians
    1.57
    .’”
    1.56
    Activations Density 0.014%

    No Known Activations