© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35135
    Prev
    Next
    INDEX
    Explanations

    qualifying phrases before commas

    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_22/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
     such
    -1.63
     that
    -1.30
    おわりに
    -1.20
    providedIn
    -1.15
    aimerais
    -1.13
    を買う
    -1.11
    をや
    -1.10
     this
    -1.10
    //};
    -1.09
     which
    -1.08
    POSITIVE LOGITS
    Another
    1.13
    อีก
    1.12
    它的
    1.07
     abordagem
    1.03
     Именно
    1.02
    ↵↵
    1.02
    ,
    1.02
    Preparazione
    0.99
    还有
    0.99
    yorum
    0.99
    Activations Density 0.040%

    No Known Activations