© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 44261
    Prev
    Next
    INDEX
    Explanations

    place names and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     happening
    1.08
     đen
    1.02
    η
    1.02
    üt
    1.00
    ्टी
    1.00
    ό
    0.99
     lumière
    0.98
    ل
    0.97
    ʸ
    0.97
    ка
    0.97
    POSITIVE LOGITS
    i
    1.33
    I
    1.25
     Alic
    1.18
     pronouns
    1.15
     eigenfunctions
    1.15
    iid
    1.11
     وعلى
    1.08
     hypersurfaces
    1.08
    \}_{
    1.05
     demean
    1.05
    Activations Density 0.000%

    No Known Activations