© 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. 60859
    Prev
    Next
    INDEX
    Explanations

    the `[word1]` `[word2]`

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

    exploring early development and inquiry

    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
     владе
    0.52
    ي
    0.51
     वाले
    0.50
    ла
    0.50
    اقة
    0.49
    ranking
    0.48
     낮
    0.48
    ลา
    0.47
    ggle
    0.47
     Его
    0.46
    POSITIVE LOGITS
     investigators
    0.48
    驄
    0.43
     authors
    0.43
     preempt
    0.43
     autonomously
    0.42
     posits
    0.41
     embry
    0.41
     braids
    0.41
     incentiv
    0.40
     enzym
    0.40
    Activations Density 0.000%

    No Known Activations