© 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. 12766
    Prev
    Next
    INDEX
    Explanations

    cinematography or cardiomyopathy

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

    words related to film production like "cinematography" and "CIFilter".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    }$,
    -2.44
     pengusaha
    -2.39
     nacido
    -2.36
     triumphs
    -2.33
    鲻
    -2.30
     semua
    -2.28
    .''
    -2.27
    ஂ
    -2.27
     incluido
    -2.23
    )));
    
    -2.23
    POSITIVE LOGITS
     ‘
    2.50
    珰
    2.42
    觧
    2.38
    ,
    2.31
    アイス
    2.20
    1
    2.20
    .
    2.11
     ziem
    2.09
    ”
    2.09
    The
    2.02
    Activations Density 0.003%

    No Known Activations