© 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-65K
    7. 11793
    Prev
    Next
    INDEX
    Explanations

    Please enter, must be

    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_65k_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
    icità
    0.42
    écution
    0.42
    🥋
    0.42
    🏬
    0.42
     అంశ
    0.42
    有可能
    0.41
    こともある
    0.40
     тобой
    0.40
    শিংটন
    0.40
    SSFWorkbook
    0.40
    POSITIVE LOGITS
     please
    0.58
     must
    0.53
    please
    0.52
     harus
    0.51
    must
    0.49
    Please
    0.49
     Please
    0.49
     phải
    0.49
    T
    0.47
    请
    0.46
    Activations Density 0.103%

    No Known Activations