© 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. 209736
    Prev
    Next
    INDEX
    Explanations

    purpose and services

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

    absorbed memory and understanding

    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
     rangkaian
    0.49
    ರಿ
    0.48
    اک
    0.47
    た
    0.46
     aliv
    0.46
    ಸ್
    0.45
    協議
    0.45
     miras
    0.45
    登録
    0.44
    ⸝
    0.44
    POSITIVE LOGITS
     Flexibility
    0.44
     difficult
    0.44
     kg
    0.43
     없습니다
    0.43
    iment
    0.43
    Integration
    0.42
     competition
    0.42
     Engagement
    0.42
     Wettbewer
    0.42
     suggesting
    0.41
    Activations Density 0.001%

    No Known Activations