© 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. 43850
    Prev
    Next
    INDEX
    Explanations

    numbers in dates and dimensions

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

    pun and punny names

    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
    aved
    0.46
     plight
    0.45
     cih
    0.43
     fanciful
    0.43
     questi
    0.40
     ח
    0.40
    otions
    0.40
    慈善
    0.40
    oggetto
    0.39
    acija
    0.39
    POSITIVE LOGITS
    Switcher
    0.44
     bền
    0.43
     باذن
    0.42
    犄
    0.41
     désormais
    0.41
    ून्य
    0.41
    NoError
    0.40
     Guarant
    0.40
    র্ডার
    0.40
     downsizing
    0.39
    Activations Density 0.000%

    No Known Activations