© 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. 34746
    Prev
    Next
    INDEX
    Explanations

    events and time sequences

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

    use of function

    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
    ಿನ
    0.55
    ತ್ರಿ
    0.50
    ай
    0.47
    of
    0.47
    ग
    0.47
    車
    0.46
    имо
    0.45
    ⵥ
    0.43
    ग्र
    0.42
    ಲಾ
    0.42
    POSITIVE LOGITS
     নাও
    0.51
     दिलचस्प
    0.49
     Soils
    0.49
     Artificial
    0.48
     Butterworth
    0.46
     Raiders
    0.46
     Weiner
    0.46
     Aid
    0.45
     İş
    0.45
     Edward
    0.45
    Activations Density 0.000%

    No Known Activations