© 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. 21104
    Prev
    Next
    INDEX
    Explanations

    expressing necessity

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

    broken down into

    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
    Large
    0.55
    il
    0.54
    {
    0.52
    为
    0.52
    ل
    0.51
    في
    0.50
    அ
    0.49
    发动
    0.48
    {(
    0.48
    л
    0.48
    POSITIVE LOGITS
     grammaticality
    0.48
     transparence
    0.47
     UIStoryboard
    0.44
    멩
    0.44
     фонбет
    0.44
     cupcakes
    0.43
     determinación
    0.43
     cuáles
    0.43
     DETERMIN
    0.41
     semanas
    0.41
    Activations Density 0.000%

    No Known Activations