© 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. 66681
    Prev
    Next
    INDEX
    Explanations

    who spoke, always provide

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

    detailing or defining restrictions

    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
     Lidl
    0.46
     اصلي
    0.45
    帏
    0.45
    荻
    0.44
    ུ
    0.44
     vivere
    0.44
    orak
    0.43
     indice
    0.42
     जुन
    0.42
    윰
    0.42
    POSITIVE LOGITS
    ны
    0.60
    ointments
    0.59
    ні
    0.53
    striction
    0.52
    Relationship
    0.49
    result
    0.48
    restrictions
    0.48
    mimeTypes
    0.47
    ческая
    0.47
    association
    0.46
    Activations Density 0.001%

    No Known Activations