© 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. 11956
    Prev
    Next
    INDEX
    Explanations

    Objective-C method names

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

    type casting operations in programming code, particularly the closing parenthesis of a type cast.

    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
    憷
    -2.75
    <td>
    -2.55
    狲
    -2.50
    
    -2.36
     帅气
    -2.34
     降
    -2.30
    ſſen
    -2.30
    I
    -2.20
     torba
    -2.17
     écart
    -2.16
    POSITIVE LOGITS
     There
    2.94
     are
    2.73
     Там
    2.44
    蔦
    2.41
     echoes
    2.36
    ほうが
    2.30
    荩
    2.16
    夘
    2.14
    IGRATION
    2.09
    寕
    2.08
    Activations Density 0.002%

    No Known Activations