© 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. 32602
    Prev
    Next
    INDEX
    Explanations

    factoring quadratic expressions

    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
    叓
    0.40
     ಸ್ಪ
    0.39
     세제곱
    0.39
    始
    0.39
     Borel
    0.38
    lub
    0.38
     அச
    0.37
     كيل
    0.37
    transformers
    0.37
    princip
    0.37
    POSITIVE LOGITS
     (+
    0.42
    (+
    0.40
    িণ
    0.40
    (+)
    0.39
     MIDDLE
    0.39
     [+
    0.39
     Foil
    0.38
     tempHeader
    0.37
     FOLLOWING
    0.37
     +"
    0.37
    Activations Density 0.010%

    No Known Activations