© 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. 163336
    Prev
    Next
    INDEX
    Explanations

    heart disease, death, cadence, read, remember, reflection

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

    rigorously vetted

    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
    !">
    0.50
    ಾ
    0.45
     PICK
    0.44
     pou
    0.44
     emptying
    0.44
     milioni
    0.44
    ו
    0.44
     indust
    0.43
     hadiah
    0.43
     âmbito
    0.42
    POSITIVE LOGITS
    TargetPath
    0.51
     Dubois
    0.44
    冯
    0.43
    骡
    0.42
    KHTML
    0.41
    机
    0.41
    ยอม
    0.40
    Reasoner
    0.40
    webContents
    0.40
    规
    0.39
    Activations Density 0.002%

    No Known Activations