© 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. 40-GEMMASCOPE-2-RES-262K
    7. 111696
    Prev
    Next
    INDEX
    Explanations

    segment decline rate

    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_40_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
     swag
    0.38
    䍧
    0.38
     Ads
    0.37
     ಜಿಲ್ಲ
    0.37
     zeker
    0.36
    ैटिन
    0.36
     proxim
    0.36
    Ĭ
    0.36
    avanja
    0.35
    offsetLeft
    0.35
    POSITIVE LOGITS
    PROGRAM
    0.37
    ოთ
    0.36
     ہار
    0.35
    glazed
    0.35
     PUBL
    0.35
     համ
    0.35
    琇
    0.35
     NUM
    0.34
    ว
    0.34
     retrou
    0.34
    Activations Density 0.000%

    No Known Activations