© 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. 222376
    Prev
    Next
    INDEX
    Explanations

    costs and amounts

    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
    FlashValue
    0.49
     wildfire
    0.46
     serviceable
    0.46
    ➘
    0.45
    campfire
    0.45
     warrantless
    0.44
    NEUTRON
    0.43
     piecewise
    0.43
    ទ្
    0.43
    addChild
    0.43
    POSITIVE LOGITS
     jadi
    0.46
     mais
    0.42
    izare
    0.40
     ch
    0.40
     we
    0.40
    君
    0.40
     Jadi
    0.39
     Ext
    0.39
    0.38
     bara
    0.38
    Activations Density 0.001%

    No Known Activations