© 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. 16-GEMMASCOPE-2-RES-262K
    7. 46205
    Prev
    Next
    INDEX
    Explanations

    tap into something

    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
    z
    1.09
     당신
    0.88
    বন্ত
    0.84
    zov
    0.84
    änd
    0.81
    UC
    0.80
     යා
    0.79
     रुद्र
    0.75
    iana
    0.75
    ana
    0.74
    POSITIVE LOGITS
    ’
    1.08
     to
    0.98
    ri
    0.97
    ラ
    0.97
    ুল
    0.96
    س
    0.95
    ”
    0.93
    u
    0.92
    Tap
    0.92
    다
    0.92
    Activations Density 0.004%

    No Known Activations