© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28084
    Prev
    Next
    INDEX
    Explanations

    age and demographic information

    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
     주로
    0.50
     puissance
    0.46
    畬
    0.45
    ۚ
    0.42
    ᠶ
    0.41
     غالب
    0.40
     преимущественно
    0.40
    ’:
    0.40
     utilising
    0.40
     수준
    0.39
    POSITIVE LOGITS
    emetery
    0.40
     traditional
    0.38
     extraneous
    0.37
    specification
    0.37
    💟
    0.37
     ranges
    0.36
    mouseout
    0.36
     mysterious
    0.36
    ledged
    0.36
    residential
    0.35
    Activations Density 0.001%

    No Known Activations