© 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. 58775
    Prev
    Next
    INDEX
    Explanations

    no followed by negative or restrictive words

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

    No followed by nouns

    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
     ovvero
    0.46
     stellar
    0.43
    chemic
    0.42
     all
    0.41
    ></
    0.41
     unsuccessfully
    0.41
    ilerden
    0.41
    </u>
    0.40
     trac
    0.40
    ่
    0.40
    POSITIVE LOGITS
     mérite
    0.52
     ডাক
    0.52
     Беларусі
    0.48
     এখানে
    0.46
     இதில்
    0.46
     whatsoever
    0.46
    Під
    0.45
    Мак
    0.44
     tenei
    0.44
    ἔ
    0.44
    Activations Density 0.066%

    No Known Activations