© 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. 15189
    Prev
    Next
    INDEX
    Explanations

    expressing thanks and positive feedback

    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
     Biblioteca
    0.49
    伊朗
    0.40
    ちなみに
    0.39
     двух
    0.39
    ։
    0.38
    ⊕
    0.38
     Gregorian
    0.38
     घोषणा
    0.37
     Azərbaycan
    0.37
    ❐
    0.37
    POSITIVE LOGITS
     매우
    0.46
     very
    0.46
     rockets
    0.40
    非常的
    0.39
     rất
    0.38
     excellently
    0.38
     항상
    0.38
     bardzo
    0.38
    非常好
    0.38
    va
    0.37
    Activations Density 0.000%

    No Known Activations