© 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. 40-GEMMASCOPE-2-RES-262K
    7. 109244
    Prev
    Next
    INDEX
    Explanations

    calculator buttons and clear

    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_40_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
    立
    0.44
    Alexandra
    0.43
    衚
    0.41
     marito
    0.41
    Edinburgh
    0.40
    Tareas
    0.40
    jahter
    0.39
     স্বায়ত্ত
    0.39
    ნიშვნელ
    0.39
    Კ
    0.39
    POSITIVE LOGITS
     Clear
    0.59
     Delete
    0.59
     AC
    0.58
     MC
    0.55
     clear
    0.54
     CE
    0.51
     zeros
    0.51
     zeroes
    0.51
     zero
    0.49
    Delete
    0.49
    Activations Density 0.019%

    No Known Activations