© 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. 161658
    Prev
    Next
    INDEX
    Explanations

    sharing famous saxophone door air

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

    primary language, Person A, 5g nr, stack of

    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
    ስቃ
    0.53
     बताओ
    0.52
     areal
    0.52
     والله
    0.47
     noh
    0.47
     cybers
    0.46
     σημαν
    0.46
     從
    0.46
     microfiber
    0.45
    ayan
    0.45
    POSITIVE LOGITS
    らは
    0.47
    ların
    0.45
    us
    0.45
    息
    0.44
     Courthouse
    0.43
    '>
    0.43
    <0xAE>
    0.43
    '><
    0.42
    Mi
    0.41
     Mi
    0.40
    Activations Density 0.000%

    No Known Activations