© 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. 245014
    Prev
    Next
    INDEX
    Explanations

    protect them

    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
    0.56
     crean
    0.47
    ۵
    0.44
     crea
    0.44
     excre
    0.42
     are
    0.41
     excretion
    0.41
    󠁬
    0.41
     weaponry
    0.41
    ونا
    0.40
    POSITIVE LOGITS
     भाव
    0.46
     उत्सुक
    0.45
    ɩ
    0.44
    受到
    0.44
    akov
    0.43
    alu
    0.43
    itelist
    0.43
     پڑھی
    0.43
    replacement
    0.42
     ఉద్య
    0.42
    Activations Density 0.001%

    No Known Activations