© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202957
    Prev
    Next
    INDEX
    Explanations

    specific templates

    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_31_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
     Tolerance
    0.40
    语文
    0.38
     concentric
    0.38
    نة
    0.37
    喑
    0.36
    ေါ
    0.35
     tolerances
    0.35
     छैन
    0.35
    нология
    0.35
     данни
    0.35
    POSITIVE LOGITS
     കൂടുതൽ
    0.53
     aumentare
    0.52
     ajudar
    0.46
    ad
    0.45
     aumentar
    0.45
     melhorar
    0.44
    avar
    0.44
     migliorare
    0.44
     વધુ
    0.43
    Ｂ
    0.43
    Activations Density 0.001%

    No Known Activations