© 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. 201833
    Prev
    Next
    INDEX
    Explanations

    Athabasca University

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

    story points

    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
    ंडर
    0.46
     это
    0.46
    phs
    0.45
    h
    0.45
    ೂರ್ವ
    0.44
    科
    0.44
     essere
    0.43
    Kc
    0.43
    it
    0.42
     avaient
    0.42
    POSITIVE LOGITS
    🦾
    0.47
    𝕠
    0.44
     🥰
    0.42
    を実現
    0.41
     🤗
    0.41
     สามารถ
    0.40
    ุน
    0.39
    🤲
    0.39
    ))){
    0.39
     reassurance
    0.38
    Activations Density 0.001%

    No Known Activations