© 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. 84395
    Prev
    Next
    INDEX
    Explanations

    related to subsequent concepts

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

    interviews, essential, passions, apples

    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
    _
    0.43
     Tort
    0.42
     nincs
    0.41
     presup
    0.40
    ’
    0.39
     volna
    0.39
     pledge
    0.39
     syllabus
    0.39
     Running
    0.38
     Sunset
    0.38
    POSITIVE LOGITS
    ሊ
    0.47
    咤
    0.44
     प्रतिक्रिया
    0.44
     γνω
    0.44
    ⦿
    0.44
    迄
    0.43
    uar
    0.43
     ร
    0.41
    istique
    0.41
    Radiux
    0.41
    Activations Density 0.000%

    No Known Activations