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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 68235
    Prev
    Next
    INDEX
    Explanations

    speakers discussing

    np_acts-logits-general · gemini-2.5-flash-lite

    discussing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     نړۍ
    0.52
     toks
    0.50
     handed
    0.46
     erupted
    0.46
     成分
    0.46
     υ
    0.45
     booted
    0.45
    ’
    0.45
     (?
    0.45
     histó
    0.44
    POSITIVE LOGITS
    Peace
    0.57
    Speakers
    0.54
    Speak
    0.53
    Discuss
    0.53
    Speaker
    0.52
    務
    0.51
    Employers
    0.50
    Expense
    0.50
    Surely
    0.50
    ത്യാ
    0.50
    Activations Density 0.000%

    No Known Activations