© 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. 190375
    Prev
    Next
    INDEX
    Explanations

    academic, community, or product contexts

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

    vast background knowledge

    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
     ಆದ್ದರಿಂದ
    0.50
    ėtų
    0.50
     городах
    0.50
    蹺
    0.49
    éges
    0.48
     Städ
    0.48
    eto
    0.47
    စိတ်
    0.47
     дерева
    0.46
     इकाइयों
    0.46
    POSITIVE LOGITS
     sosok
    0.48
     truly
    0.47
    ส
    0.45
    ئی
    0.45
    the
    0.44
    یی
    0.43
     darker
    0.43
     금
    0.43
     mythological
    0.42
    ึ
    0.42
    Activations Density 0.001%

    No Known Activations