© 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. 112501
    Prev
    Next
    INDEX
    Explanations

    beginning of actions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    蒾
    -1.86
    
    -1.76
    ʻ
    -1.75
    </h1>
    -1.66
    荦
    -1.64
    嫱
    -1.60
     сент
    -1.52
    栳
    -1.52
    璈
    -1.50
    ⇿
    -1.50
    POSITIVE LOGITS
     from
    1.65
    ンスター
    1.53
     with
    1.51
     skriv
    1.43
    ,  
    1.38
     Bizarre
    1.38
    果然
    1.36
     Described
    1.35
     osal
    1.35
     visibilidad
    1.33
    Activations Density 0.031%

    No Known Activations