© 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. 48325
    Prev
    Next
    INDEX
    Explanations

    phrases with 'by' or 'will' or 'would'

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

    special cases: (), Russian, oxygen, bind, required

    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
    Examples
    0.53
    م
    0.51
    ن
    0.46
     серьез
    0.46
    बर्ग
    0.45
    னைய
    0.45
    Estate
    0.43
    Work
    0.43
    Circle
    0.43
    Optim
    0.43
    POSITIVE LOGITS
    marker
    0.50
     counter
    0.46
    ীতে
    0.46
    കൾ
    0.46
    )
    0.46
    )))
    0.45
    áč
    0.44
     vacanam
    0.44
     );
    0.44
     nito
    0.44
    Activations Density 0.000%

    No Known Activations