© 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. 83817
    Prev
    Next
    INDEX
    Explanations

    end of sentence, start of item

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

    my list

    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
    度が
    0.47
    的技术
    0.47
     стратегия
    0.46
     як
    0.45
    ენ
    0.44
    πα
    0.44
    ﺗ
    0.43
     선수
    0.43
    Литература
    0.43
     estratégica
    0.43
    POSITIVE LOGITS
    iese
    0.46
    ould
    0.46
    otten
    0.45
    zné
    0.45
     fusible
    0.44
    binoculars
    0.44
    stant
    0.43
     welt
    0.43
    do
    0.42
    to
    0.42
    Activations Density 0.001%

    No Known Activations