© 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. 86405
    Prev
    Next
    INDEX
    Explanations

    makes two

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

    common misconceptions and worries

    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
     করো
    0.47
    is
    0.46
    t
    0.46
    uator
    0.44
    ی
    0.43
     зат
    0.42
    apods
    0.42
    u
    0.41
    zat
    0.41
    imhe
    0.40
    POSITIVE LOGITS
     esperienze
    0.53
     etkinlik
    0.52
     menimbulkan
    0.51
    ד
    0.50
     tedesco
    0.50
    ESS
    0.50
    PSC
    0.48
     pagine
    0.48
     kaldır
    0.47
     kilometer
    0.47
    Activations Density 0.000%

    No Known Activations