© 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. 21324
    Prev
    Next
    INDEX
    Explanations

    academic and legal contexts

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

    a, one, or uniform

    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
     예를
    0.46
     exempel
    0.45
     eksempel
    0.42
     például
    0.41
     مثلا
    0.41
    につなが
    0.40
    ◯
    0.40
     Amtrak
    0.39
     použ
    0.39
    例
    0.39
    POSITIVE LOGITS
     Abteilung
    0.47
    uries
    0.44
     debilitating
    0.41
    Department
    0.41
    bicara
    0.40
     DEPARTMENT
    0.39
     oud
    0.39
     frightening
    0.39
    फ्र
    0.39
     fra
    0.38
    Activations Density 0.000%

    No Known Activations