© 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. 199998
    Prev
    Next
    INDEX
    Explanations

    academic, travel, or technical settings

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

    artistic, Ozempic, programming concepts

    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
    財布
    0.48
     Lies
    0.47
    繚
    0.45
     coaching
    0.45
    EUR
    0.44
     biodivers
    0.43
     вя
    0.42
     geï
    0.42
     χώ
    0.42
     afsl
    0.42
    POSITIVE LOGITS
     ordered
    0.47
     तेंदुलकर
    0.46
    StudentRecord
    0.46
    sure
    0.45
    ینی
    0.44
    码
    0.43
    。『
    0.43
    mosquito
    0.42
     invert
    0.42
    lerde
    0.42
    Activations Density 0.000%

    No Known Activations