© 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. 49680
    Prev
    Next
    INDEX
    Explanations

    accessed on date

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

    learn more, access, feel, arguments, difficult

    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
    patx
    0.47
    brokers
    0.46
    BROOK
    0.46
     रखेंगे
    0.45
     abstain
    0.45
    永
    0.44
     fxe
    0.43
     layoffs
    0.43
    Biden
    0.43
     excused
    0.43
    POSITIVE LOGITS
     Damage
    0.55
     Bands
    0.54
    伤
    0.50
     Feet
    0.50
     Companion
    0.49
     Canoe
    0.49
     Compart
    0.48
     companion
    0.48
     Sampling
    0.48
     durch
    0.48
    Activations Density 0.001%

    No Known Activations