© 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. 223563
    Prev
    Next
    INDEX
    Explanations

    payment or access

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

    AI limitations and abstract concepts

    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
    nel
    0.49
    steering
    0.49
    ný
    0.48
    title
    0.47
    صل
    0.47
    ných
    0.47
    籵
    0.47
    在新
    0.46
    connected
    0.46
    amos
    0.45
    POSITIVE LOGITS
    वारीत
    0.46
    ⨯
    0.45
    ⑤
    0.44
     decompositions
    0.43
     isomorphisms
    0.43
     Gericht
    0.42
     ربعه
    0.42
     organelles
    0.42
    ◽
    0.42
    ℝ
    0.41
    Activations Density 0.000%

    No Known Activations