© 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. 217598
    Prev
    Next
    INDEX
    Explanations

    sensitive aspects

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

    groups open, crucial for, used for

    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
     outs
    0.51
     unrel
    0.46
    उंस
    0.46
    Hyderabad
    0.46
    दाश्त
    0.46
     antena
    0.46
    akkhan
    0.45
    ോ
    0.45
     cursorPos
    0.45
     unst
    0.44
    POSITIVE LOGITS
    elle
    0.50
    quoi
    0.49
    amiento
    0.49
     توا
    0.48
    ко
    0.45
    avo
    0.45
    equilibrium
    0.45
    it
    0.44
    י
    0.44
    es
    0.44
    Activations Density 0.001%

    No Known Activations