© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 145601
    Prev
    Next
    INDEX
    Explanations

    different languages or concepts

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

    greetings and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ય
    0.46
    סטי
    0.45
    ס
    0.44
    say
    0.44
    נק
    0.43
    שר
    0.43
    通知
    0.43
    שי
    0.42
    蜚
    0.41
     ফুলের
    0.40
    POSITIVE LOGITS
     perplexed
    0.49
     വ്യത്യ
    0.49
     handen
    0.48
    wej
    0.48
     เช่น
    0.47
    穼
    0.47
     giggle
    0.46
     되어
    0.46
     forskellige
    0.46
     forskjellige
    0.46
    Activations Density 0.000%

    No Known Activations