© 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. 55990
    Prev
    Next
    INDEX
    Explanations

    TRS headphone

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

    setting up situations or conditions

    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
    ُ
    0.49
    *,
    0.46
    brella
    0.45
    ⌓
    0.42
     مات
    0.41
     numéro
    0.40
     المط
    0.39
     الثلاث
    0.39
    ـ
    0.39
     الجما
    0.38
    POSITIVE LOGITS
     verbose
    0.44
     initializes
    0.44
     intimated
    0.42
     SMTP
    0.41
     Entrance
    0.40
     प्रकाशित
    0.40
     initialized
    0.39
     entrance
    0.39
     STATUS
    0.38
     adjustable
    0.38
    Activations Density 0.000%

    No Known Activations