© 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. 189996
    Prev
    Next
    INDEX
    Explanations

    local community presence

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

    AI language models

    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
     therapeut
    0.49
     renferme
    0.48
     worden
    0.45
     thiol
    0.45
    谆
    0.42
     alebo
    0.41
     oder
    0.40
    ⊗
    0.40
    ,!
    0.40
    參
    0.40
    POSITIVE LOGITS
     ഒഴിവാ
    0.56
     جلوگیری
    0.49
     ሙሉ
    0.46
     déplacements
    0.46
     छुपा
    0.46
     अंड
    0.46
     छुट्टी
    0.45
     చూపు
    0.45
    eş
    0.45
     ModelState
    0.44
    Activations Density 0.001%

    No Known Activations