© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143479
    Prev
    Next
    INDEX
    Explanations

    phrases after 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_31_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
    嫄
    0.51
     پورے
    0.46
     prerequisites
    0.45
    疫苗
    0.45
    আমর
    0.44
    ₕ
    0.44
     সমুদ
    0.43
    বাহ
    0.43
     contexts
    0.43
     textbook
    0.43
    POSITIVE LOGITS
    ];
    0.45
    ";
    0.45
    ek
    0.44
     แต่
    0.43
     Pero
    0.42
     pero
    0.42
    ire
    0.42
    ".
    0.42
     покра
    0.41
     주로
    0.41
    Activations Density 0.009%

    No Known Activations