© 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. 39996
    Prev
    Next
    INDEX
    Explanations

    English plurals or past tense `-ed`

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

    multiple languages

    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
    鏽
    0.41
     був
    0.41
     név
    0.41
    ogen
    0.38
     byl
    0.37
     komplet
    0.37
    เส
    0.36
    ensitive
    0.36
    }={
    0.36
     OV
    0.35
    POSITIVE LOGITS
     economici
    0.47
     Idani
    0.44
    バイ
    0.40
    ManyToMany
    0.40
     স্বচ্ছ
    0.40
     યોગ્ય
    0.40
    ibilités
    0.40
    nemouth
    0.39
    ﮑ
    0.39
    gwood
    0.39
    Activations Density 0.000%

    No Known Activations