© 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. 172713
    Prev
    Next
    INDEX
    Explanations

    articles or prepositions following common words

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

    descendants, household, logic

    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
    Manu
    0.46
     Mortality
    0.45
    鍔
    0.45
     Manu
    0.45
    豪
    0.44
     -=
    0.43
    瞥
    0.43
    Brit
    0.43
    {
    0.43
    struct
    0.42
    POSITIVE LOGITS
     abgerufen
    0.46
     уні
    0.45
    ത്തര
    0.44
     adimensional
    0.44
    웨어
    0.43
     Kommentar
    0.42
    lng
    0.42
     Pendidikan
    0.41
     県
    0.41
    RICAL
    0.41
    Activations Density 0.001%

    No Known Activations