© 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. 43789
    Prev
    Next
    INDEX
    Explanations

    words within sentences

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

    instructions and commands

    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
    q
    0.65
    ky
    0.63
    ko
    0.63
    kar
    0.59
    ha
    0.57
    ý
    0.57
    ă
    0.52
    ve
    0.52
    ions
    0.51
    vi
    0.51
    POSITIVE LOGITS
     superson
    0.51
    屒
    0.48
    િજા
    0.48
    ECON
    0.48
     według
    0.48
    䐍
    0.48
    NUCLEAR
    0.47
     lanjutan
    0.47
    LEXPORT
    0.46
    ⬮
    0.46
    Activations Density 0.001%

    No Known Activations