© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9694
    Prev
    Next
    INDEX
    Explanations

    was + verb/preposition

    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
    ри
    1.02
    ፣
    0.95
    тся
    0.94
    t
    0.91
     económicos
    0.91
    withstanding
    0.88
    ногие
    0.88
    ណ៍
    0.87
    которые
    0.86
    ους
    0.86
    POSITIVE LOGITS
     auparavant
    1.42
     autrefois
    1.41
     anteriormente
    1.34
    ों
    1.20
     negara
    1.15
    s
    1.14
    لي
    1.10
     Wunsch
    1.10
    $
    1.09
    س
    1.08
    Activations Density 0.069%

    No Known Activations