© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8707
    Prev
    Next
    INDEX
    Explanations

    street names and numbers

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

    988lifeline

    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_40_width_16k_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
    ustus
    0.44
    ното
    0.44
    ็
    0.42
     foss
    0.42
    ället
    0.41
    INUS
    0.40
     ies
    0.40
    िक
    0.39
     kre
    0.39
     творчества
    0.39
    POSITIVE LOGITS
    cini
    0.47
    zynarod
    0.47
    ci
    0.43
    ership
    0.43
    p
    0.43
    c
    0.42
    ecie
    0.42
    pir
    0.41
     நாம
    0.40
    rush
    0.40
    Activations Density 0.217%

    No Known Activations