© 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. 46864
    Prev
    Next
    INDEX
    Explanations

    Theresa May pint

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

    multi-word 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
     وکړئ
    0.44
    PCR
    0.42
    钽
    0.42
    ્સ
    0.41
    institut
    0.41
    ᖇ
    0.41
    Nunca
    0.40
    焜
    0.40
     کردم
    0.40
    棪
    0.40
    POSITIVE LOGITS
     passengers
    0.49
     India
    0.45
     Passengers
    0.42
     comparatively
    0.41
     adjoining
    0.41
     někter
    0.41
     vlak
    0.40
     plains
    0.39
    随便
    0.39
     beneath
    0.38
    Activations Density 0.001%

    No Known Activations