© 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. 147809
    Prev
    Next
    INDEX
    Explanations

    capital city

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

    gay sex or taboo

    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
     일반
    0.46
     安
    0.46
     प्रताप
    0.46
     insights
    0.44
    ாளர்கள்
    0.44
    ilust
    0.44
    prus
    0.44
    yj
    0.44
     عام
    0.43
     reag
    0.43
    POSITIVE LOGITS
    ㈤
    0.50
    Checkpoint
    0.45
    Organiz
    0.42
     Sympt
    0.42
     numai
    0.42
     Diagnosis
    0.42
    wxT
    0.42
    '),
    0.42
    )=\
    0.41
     Task
    0.41
    Activations Density 0.001%

    No Known Activations