© 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. 155533
    Prev
    Next
    INDEX
    Explanations

    noun followed by preposition/conjunction

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

    details how

    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
    ق
    0.51
     बगल
    0.49
    undering
    0.47
    피
    0.47
     अल्कोहल
    0.46
    ులు
    0.46
    ➚
    0.46
     Prayers
    0.46
     PUBLIC
    0.46
    수
    0.46
    POSITIVE LOGITS
     interpol
    0.45
     去
    0.44
     pergi
    0.44
     setengah
    0.44
    ↵
    0.43
     hex
    0.43
     vutto
    0.43
     ellipses
    0.43
     filtr
    0.42
     assimil
    0.42
    Activations Density 0.001%

    No Known Activations