© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 149629
    Prev
    Next
    INDEX
    Explanations

    custom build

    np_acts-logits-general · gemini-2.5-flash-lite

    states or origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝑳
    0.59
    𝑪
    0.53
    hills
    0.50
    dif
    0.50
     कठिन
    0.50
     oppressive
    0.50
    𝑮
    0.49
    atter
    0.48
    russ
    0.48
    Additive
    0.46
    POSITIVE LOGITS
     نحن
    0.48
     indiquant
    0.48
    。
    0.46
    ۔
    0.46
    一块
    0.45
    اضره
    0.45
     reconna
    0.44
     Worker
    0.44
     enumeration
    0.43
     Enumer
    0.43
    Activations Density 0.000%

    No Known Activations