© 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. 37152
    Prev
    Next
    INDEX
    Explanations

    retro design

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

    past tense verbs and common prepositions

    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
     线
    0.48
     海
    0.48
     棉
    0.48
     一个
    0.46
    谩
    0.46
     지속
    0.46
     Και
    0.45
     高
    0.45
     ricerca
    0.44
     开发
    0.44
    POSITIVE LOGITS
    ều
    0.48
    ives
    0.47
    तीने
    0.44
    Spe
    0.43
    oside
    0.43
     dodge
    0.43
     hy
    0.42
    Nob
    0.42
     dimmer
    0.41
     appell
    0.41
    Activations Density 0.000%

    No Known Activations