© 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. 6803
    Prev
    Next
    INDEX
    Explanations

    keywords followed by punctuation or context

    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
    ta
    0.59
    ts
    0.47
    ”
    0.46
    da
    0.44
    선
    0.44
     הזה
    0.43
    Q
    0.43
    rov
    0.42
    zar
    0.41
    紀
    0.40
    POSITIVE LOGITS
    wrs
    0.50
     landen
    0.50
    werken
    0.50
    wunsch
    0.50
     autrefois
    0.50
    раб
    0.50
    ഗ്
    0.49
    ங்கம்
    0.49
     foodstuffs
    0.49
    торин
    0.49
    Activations Density 0.000%

    No Known Activations