© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8050
    Prev
    Next
    INDEX
    Explanations

    leaving or departing

    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_31_width_16k_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
    或
    0.52
     или
    0.51
     või
    0.47
     veya
    0.46
     hoặc
    0.45
     或
    0.43
    letter
    0.43
     அல்லது
    0.42
    หรือ
    0.40
     또는
    0.39
    POSITIVE LOGITS
     regresar
    0.57
    いていた
    0.46
     constate
    0.45
     empecé
    0.45
     returning
    0.45
     cutest
    0.45
    帰
    0.44
     estavam
    0.44
     extranj
    0.44
     malheureusement
    0.44
    Activations Density 0.044%

    No Known Activations