© 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. 84253
    Prev
    Next
    INDEX
    Explanations

    future, holiday, calendars, person

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

    connection and shared defiance

    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
     Bởi
    0.46
     পুরু
    0.45
    decorative
    0.45
    playable
    0.45
    ব
    0.44
    苣
    0.44
    ал
    0.44
    账
    0.44
     રીતે
    0.43
    техни
    0.43
    POSITIVE LOGITS
     anunci
    0.57
     magazines
    0.49
     controle
    0.49
    ked
    0.48
     polít
    0.45
     subdiv
    0.45
     incriminating
    0.45
     dlg
    0.45
     imposition
    0.45
     definit
    0.45
    Activations Density 0.001%

    No Known Activations