© 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. 29950
    Prev
    Next
    INDEX
    Explanations

    that sounds

    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
    ൗ
    0.47
     incred
    0.46
    KOV
    0.43
     commendable
    0.42
    ง
    0.41
     aire
    0.41
     couches
    0.41
    欣
    0.40
    )
    0.40
    QUIS
    0.39
    POSITIVE LOGITS
    学校
    0.45
    描き
    0.42
    ကြည်
    0.41
     சொல்
    0.41
    Editorial
    0.40
    警告
    0.40
     请求
    0.39
     Charities
    0.38
    otics
    0.37
    delà
    0.37
    Activations Density 0.009%

    No Known Activations