© 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. 126363
    Prev
    Next
    INDEX
    Explanations

    colon or quotation mark

    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
    垩
    0.44
     Astrophysics
    0.41
     คณิต
    0.41
     каждого
    0.40
     않았
    0.40
     Bologna
    0.40
    
    0.40
     jeweils
    0.40
     각각
    0.40
     않았다
    0.39
    POSITIVE LOGITS
    n
    0.51
    str
    0.51
    top
    0.50
    tribe
    0.50
    consolid
    0.46
    4
    0.46
    tope
    0.45
    3
    0.44
     contribu
    0.44
    change
    0.44
    Activations Density 0.010%

    No Known Activations