© 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. 34-GEMMASCOPE-RES-131K
    7. 63196
    Prev
    Next
    INDEX
    Explanations

    talking about

    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_34/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
    aperto
    -1.20
    －－－－
    -1.09
    ＝＝＝＝
    -1.08
    ＊＊＊＊
    -1.05
    Припев
    -1.04
    際は
    -1.02
    Durata
    -1.02
    感じが
    -1.02
    Between
    -1.02
    īb
    -1.01
    POSITIVE LOGITS
     about
    12.06
    about
    5.16
    About
    4.78
     About
    4.59
     tentang
    4.53
    关于
    4.34
     ABOUT
    4.16
    ABOUT
    3.94
     acerca
    3.88
     về
    3.75
    Activations Density 0.772%

    No Known Activations