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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100159
    Prev
    Next
    INDEX
    Explanations

    information not verified

    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
    Tensor
    0.43
    Encycl
    0.42
    ेंसिल
    0.42
    LaTeX
    0.40
    Experiment
    0.40
    ország
    0.40
     NVIDIA
    0.39
    
    0.39
    Edited
    0.39
    Texture
    0.39
    POSITIVE LOGITS
     yard
    0.45
     grove
    0.44
     refuge
    0.44
     plates
    0.43
     shades
    0.43
     backdoor
    0.41
     sump
    0.41
    klady
    0.41
     valley
    0.40
     booty
    0.40
    Activations Density 0.001%

    No Known Activations