© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 29393
    Prev
    Next
    INDEX
    Explanations

    ways or options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ħ
    0.49
     टेक्स्ट
    0.48
     होऊन
    0.47
     ಮಾಡುವ
    0.46
     అందు
    0.46
    ŠE
    0.46
    î
    0.46
    醣
    0.46
     فَ
    0.45
    MoodAnalyser
    0.45
    POSITIVE LOGITS
     private
    0.56
     privately
    0.56
     canned
    0.53
     secrete
    0.52
     excre
    0.50
     popular
    0.50
     specified
    0.50
     financially
    0.49
     coaches
    0.49
     ponto
    0.49
    Activations Density 0.000%

    No Known Activations