© 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. 165717
    Prev
    Next
    INDEX
    Explanations

    reflect, baptism, nothing, IPO, no

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

    Remixing and generating variations

    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
     m
    0.52
     nöt
    0.46
     Celtics
    0.46
     vì
    0.45
    ories
    0.44
     NYC
    0.44
     pickups
    0.43
    ory
    0.43
     folk
    0.43
     iPod
    0.43
    POSITIVE LOGITS
    దా
    0.52
    Work
    0.50
    ക്കാം
    0.50
    ಾ
    0.49
    ွက်
    0.48
    Export
    0.48
     travaille
    0.47
    дить
    0.47
     travail
    0.47
     Trabajo
    0.46
    Activations Density 0.001%

    No Known Activations