© 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. 137871
    Prev
    Next
    INDEX
    Explanations

    batch printing version

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

    staff room, feast, polishing

    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
     máme
    0.53
    腼
    0.50
     نتیجے
    0.48
    ]()
    0.47
     বক্তব
    0.46
    閆
    0.46
    認定
    0.46
     byli
    0.45
     বাচ্চ
    0.44
     появляются
    0.44
    POSITIVE LOGITS
     in
    0.46
    ophylline
    0.46
     tuberculosis
    0.44
     naphthalene
    0.42
     অবলম্বন
    0.41
    ustral
    0.41
     secular
    0.40
    clesiastical
    0.40
    ,
    0.40
    etva
    0.39
    Activations Density 0.000%

    No Known Activations