© 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. 17465
    Prev
    Next
    INDEX
    Explanations

    the word Web

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

    artifact creation

    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
    ｵ
    0.44
    rican
    0.43
    OC
    0.42
    ++.
    0.42
    वु
    0.40
    POC
    0.39
    +.
    0.39
     жи
    0.39
     reflect
    0.39
    뤽
    0.38
    POSITIVE LOGITS
     Parameters
    0.51
    為了
    0.48
     घेण्यासाठी
    0.45
     सर्वप्रथम
    0.44
     খুবই
    0.43
    unehmen
    0.43
     위해서는
    0.43
     Eigenschaften
    0.43
    வதற்காக
    0.43
     Voici
    0.41
    Activations Density 0.000%

    No Known Activations