© 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. 161766
    Prev
    Next
    INDEX
    Explanations

    followed by certain words

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

    steam, what, make

    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
    KING
    0.50
    ᱐
    0.48
    াস্থ্যের
    0.45
    ğaz
    0.43
    පා
    0.42
     científico
    0.42
    otipi
    0.42
    KU
    0.41
    Kyr
    0.41
    K
    0.41
    POSITIVE LOGITS
    !
    0.48
    ren
    0.47
     Prairie
    0.47
    譲
    0.46
    0.45
     陳
    0.44
    CodeDom
    0.44
     Variance
    0.44
    endif
    0.44
    tm
    0.43
    Activations Density 0.001%

    No Known Activations