© 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-65K
    7. 8443
    Prev
    Next
    INDEX
    Explanations

    report and hazard

    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_65k_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
    -
    0.31
     A
    0.29
     (
    0.29
    .
    0.28
    :
    0.28
     I
    0.27
     y
    0.26
    ,
    0.26
     v
    0.25
     S
    0.24
    POSITIVE LOGITS
    㝅
    0.26
    ্ী
    0.25
    <unused329>
    0.24
    Công
    0.24
    <unused2200>
    0.24
    ೊಂದಿಗೆ
    0.24
    郆
    0.24
    <unused326>
    0.24
    goài
    0.24
    咟
    0.24
    Activations Density 0.105%

    No Known Activations