© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 209220
    Prev
    Next
    INDEX
    Explanations

    words followed by common conjunctions or prepositions

    np_acts-logits-general · gemini-2.5-flash-lite

    joining, subject, they, once, beyond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    son
    0.41
    癜
    0.41
    SON
    0.41
    urii
    0.41
    uk
    0.40
    aupun
    0.40
    Heinz
    0.40
    дони
    0.39
    ');
    0.39
    主演
    0.39
    POSITIVE LOGITS
     humana
    0.53
     umana
    0.49
     diaria
    0.49
    分鐘
    0.48
     prazo
    0.48
    ہم
    0.46
     recursively
    0.46
    閬
    0.46
     الش
    0.45
     буты
    0.45
    Activations Density 0.000%

    No Known Activations