© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 140236
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isah
    0.47
     County
    0.47
    ling
    0.46
    ᾽
    0.45
    ita
    0.45
    ades
    0.45
    inton
    0.44
    wür
    0.44
     음악
    0.44
     Reign
    0.43
    POSITIVE LOGITS
    ن
    0.61
    നം
    0.53
     textura
    0.52
    ي
    0.52
    י
    0.51
    اب
    0.51
     secund
    0.50
    ཏ
    0.50
    鸥
    0.50
     nood
    0.50
    Activations Density 0.000%

    No Known Activations