© 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. 197054
    Prev
    Next
    INDEX
    Explanations

    homeopathic healing, specialized insects, PHP implementation

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

    words following grammatical connectors

    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
     kuy
    0.40
    穢
    0.40
     *=
    0.39
    yyati
    0.39
     saddo
    0.39
    щал
    0.38
     हाइट
    0.38
     subl
    0.38
    🅴
    0.38
     roots
    0.37
    POSITIVE LOGITS
    ielle
    0.51
     EXCHANGE
    0.45
     compagnia
    0.45
     offre
    0.44
    >}
    0.44
    缜
    0.44
     primeira
    0.43
     concluir
    0.43
     geist
    0.43
     erfolgre
    0.42
    Activations Density 0.000%

    No Known Activations