© 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. 202816
    Prev
    Next
    INDEX
    Explanations

    actions, states, or abstract ideas

    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
     was
    0.52
    id
    0.51
    p
    0.49
    ap
    0.48
    on
    0.47
    ash
    0.46
     keine
    0.46
    was
    0.46
    for
    0.45
    at
    0.44
    POSITIVE LOGITS
     ibang
    0.46
     някои
    0.45
     специализирован
    0.44
    функ
    0.44
     conclusione
    0.44
     ауди
    0.44
     المختلفة
    0.44
     SUBSTIT
    0.43
    㖣
    0.43
     एग्जाम्स
    0.43
    Activations Density 0.005%

    No Known Activations