© 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. 90401
    Prev
    Next
    INDEX
    Explanations

    facility you

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

    remembrance/memorial contexts

    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
    sum
    0.57
    物
    0.52
    ST
    0.52
    MED
    0.48
     प्रवीण
    0.47
    MAD
    0.46
    かけて
    0.46
     priem
    0.45
    T
    0.45
    SLOW
    0.45
    POSITIVE LOGITS
    apeti
    0.53
     grainy
    0.52
     棚
    0.50
     zdjęcia
    0.49
     切り
    0.47
     steril
    0.47
    czki
    0.47
     cabinets
    0.47
     깨
    0.47
     caramel
    0.47
    Activations Density 0.001%

    No Known Activations