© 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. 56673
    Prev
    Next
    INDEX
    Explanations

    often followed by colon or bolded phrase

    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
    ง
    0.51
     Decrease
    0.43
     ਜੋ
    0.43
    igrams
    0.42
    Decrease
    0.41
     Words
    0.41
    Compart
    0.41
    г
    0.41
     Meaning
    0.40
    п
    0.40
    POSITIVE LOGITS
     precursor
    0.54
     kuş
    0.47
     *,
    0.47
     ludzie
    0.46
     coastline
    0.46
     oasis
    0.46
     soared
    0.45
     otak
    0.45
     gown
    0.45
     noodle
    0.44
    Activations Density 0.001%

    No Known Activations