© 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. 100694
    Prev
    Next
    INDEX
    Explanations

    specific technical terms

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

    Use these words in #phrase_list

    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
     Knife
    0.50
     Schedule
    0.48
    截图
    0.46
     Shared
    0.45
    葚
    0.45
     Planting
    0.44
    筒
    0.44
     கீழ
    0.43
     జరిగ
    0.43
     Calend
    0.43
    POSITIVE LOGITS
    л
    0.51
     legitimate
    0.46
    ian
    0.44
    receipt
    0.44
    PHIL
    0.43
     DEPENDENCIA
    0.42
    akur
    0.42
     लागेल
    0.42
    มัน
    0.41
    є
    0.41
    Activations Density 0.000%

    No Known Activations