© 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. 104303
    Prev
    Next
    INDEX
    Explanations

    FFmpeg programming

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

    underscore characters in code identifiers, particularly after prefix characters like "ngx", "x", or "sc".

    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
     verhindert
    -1.59
    <td>
    -1.48
     And
    -1.47
    </h3>
    -1.47
     For
    -1.45
    大腿
    -1.41
     Including
    -1.41
    ятся
    -1.40
    CEAN
    -1.38
     umgekehrt
    -1.35
    POSITIVE LOGITS
    VIATIONS
    1.59
    ませんが
    1.55
    ?
    
    1.54
     προϊόν
    1.51
    íguez
    1.49
    隽
    1.48
    riwal
    1.48
    DMETHOD
    1.45
    nargs
    1.41
    ativement
    1.41
    Activations Density 0.003%

    No Known Activations