© 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. 94796
    Prev
    Next
    INDEX
    Explanations

    I need/haven followed by a word

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

    museum, now

    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
    the
    0.47
     cận
    0.46
     ہاتھ
    0.44
     subsurface
    0.44
     साथी
    0.44
     মির
    0.44
    cluded
    0.42
    )<<
    0.41
     subside
    0.41
                      
    0.41
    POSITIVE LOGITS
    е
    0.52
    ви
    0.50
    我还
    0.50
    Фи
    0.50
    ä
    0.50
    торы
    0.49
    3
    0.49
    хоро
    0.48
    экс
    0.48
    هم
    0.47
    Activations Density 0.000%

    No Known Activations