© 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. 93064
    Prev
    Next
    INDEX
    Explanations

    Fermi questions

    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
     besonders
    0.49
     obsz
    0.48
     screw
    0.47
     குறிப்பாக
    0.46
     özellikle
    0.46
     lettuce
    0.46
     noto
    0.46
     c
    0.46
     külön
    0.46
     plaintext
    0.45
    POSITIVE LOGITS
    Conservation
    0.51
    िके
    0.50
     जबलपुर
    0.47
    िस
    0.45
    Industrial
    0.44
    agriculture
    0.44
    erende
    0.44
    र
    0.44
    Imidazole
    0.44
    PIP
    0.44
    Activations Density 0.004%

    No Known Activations