© 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. 10989
    Prev
    Next
    INDEX
    Explanations

    her style or aspirations

    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
    ਕ
    0.46
     Trevelyan
    0.42
     আশ্বাস
    0.42
    以及
    0.41
     etter
    0.41
     Trabal
    0.41
     unsigned
    0.40
     synchron
    0.39
    \}_{
    0.39
     желез
    0.39
    POSITIVE LOGITS
     વપરા
    0.43
    ంబేద్
    0.42
    ạm
    0.41
    topnav
    0.41
    он
    0.41
    GYPT
    0.41
    REFLECTION
    0.41
    န်း
    0.40
    ｬ
    0.40
    ﺎ
    0.40
    Activations Density 0.005%

    No Known Activations