© 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. 46859
    Prev
    Next
    INDEX
    Explanations

    actions affecting other users or systems

    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
     ضر
    0.45
    міні
    0.43
    讃
    0.43
     مل
    0.42
     لل
    0.42
     لح
    0.41
    రిగ
    0.41
     مند
    0.40
     قائم
    0.40
     نقول
    0.40
    POSITIVE LOGITS
     sayesinde
    0.52
     nebude
    0.49
     graças
    0.48
     TESTING
    0.48
     Kap
    0.46
     ="
    0.46
     Meks
    0.46
     kode
    0.44
     grâce
    0.44
     autonome
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.