© 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. 28339
    Prev
    Next
    INDEX
    Explanations

    quick trip

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

    quick relaxation and demand

    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
    VING
    0.46
    Prés
    0.44
     сфер
    0.43
    Amplitude
    0.43
     lorsque
    0.42
     résultats
    0.42
    ᱒
    0.42
     כל
    0.40
    スプレイ
    0.40
    Raz
    0.40
    POSITIVE LOGITS
     dry
    0.47
     TLC
    0.47
    خته
    0.47
     Mariupol
    0.46
     Porto
    0.46
     AE
    0.45
     DIN
    0.44
    beth
    0.44
     CLT
    0.44
    ashed
    0.43
    Activations Density 0.000%

    No Known Activations