© 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. 122510
    Prev
    Next
    INDEX
    Explanations

    museum Hitler

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

    hospital, workplace, object, research

    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
    E
    0.61
    2
    0.60
     blessing
    0.52
    O
    0.50
     as
    0.49
     wash
    0.48
    )
    0.48
    );
    0.48
    Ac
    0.47
     than
    0.46
    POSITIVE LOGITS
     AgNO
    0.55
     તેમણે
    0.55
     கரைச
    0.52
    står
    0.52
     आण
    0.51
     பாலை
    0.51
     خودرو
    0.50
    ሳይ
    0.49
     केंद्रित
    0.49
     MgO
    0.49
    Activations Density 0.000%

    No Known Activations