© 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. 57106
    Prev
    Next
    INDEX
    Explanations

    the snow fencing

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

    mathematical notation or phrases

    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
    言葉
    0.45
    亿
    0.45
    LAND
    0.45
    Pager
    0.43
    时期
    0.42
    UKA
    0.42
    关键字
    0.41
     काळात
    0.41
    ukas
    0.41
    観察
    0.41
    POSITIVE LOGITS
     notifies
    0.51
    াড়া
    0.46
    лера
    0.46
     curled
    0.44
     composed
    0.43
     到
    0.43
     sheriff
    0.43
     Mixer
    0.43
     citizens
    0.43
     bambini
    0.43
    Activations Density 0.000%

    No Known Activations