© 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. 88265
    Prev
    Next
    INDEX
    Explanations

    proper nouns and place names

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

    therapist will do, leading text

    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
     provided
    0.53
    provided
    0.48
     Институт
    0.48
    ⚜
    0.46
     came
    0.45
     स्क्र
    0.45
     የታ
    0.45
     discussing
    0.44
    ন্স
    0.44
     કહ્યું
    0.44
    POSITIVE LOGITS
    ουν
    0.46
     wikiHow
    0.40
     아멘
    0.40
    腭
    0.39
    ampuan
    0.38
    但在
    0.38
    illeri
    0.38
     seaweed
    0.38
     subtypes
    0.38
    하니
    0.38
    Activations Density 0.000%

    No Known Activations