© 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. 158574
    Prev
    Next
    INDEX
    Explanations

    year and activities

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

    specific context and purpose

    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
    DataFrame
    0.44
    但
    0.43
    ર્મ
    0.42
     Masonic
    0.41
     wholesome
    0.40
     sailboat
    0.40
     bữa
    0.40
    琴
    0.40
    Harmony
    0.40
     ഹോളി
    0.39
    POSITIVE LOGITS
    targeted
    0.47
     خار
    0.44
     지난해
    0.44
     année
    0.43
    wide
    0.41
    昨年
    0.40
     iterated
    0.40
     lemah
    0.40
    reviewed
    0.40
     overheard
    0.40
    Activations Density 0.002%

    No Known Activations