© 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. 49582
    Prev
    Next
    INDEX
    Explanations

    Reduced energy

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

    security intelligence & algorithms

    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
     almost
    0.48
    比
    0.42
    ীব
    0.40
     почти
    0.39
    nable
    0.39
    লে
    0.38
    ほぼ
    0.38
    URE
    0.38
    ⇒
    0.38
    에도
    0.38
    POSITIVE LOGITS
     trứng
    0.46
     संग्रहण
    0.45
     Supplied
    0.45
     वेजिट
    0.44
     مخط
    0.43
     Noeud
    0.43
    ropoda
    0.42
     Handlung
    0.42
     бясплатна
    0.42
    enamefont
    0.42
    Activations Density 0.000%

    No Known Activations