© 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. 98843
    Prev
    Next
    INDEX
    Explanations

    questions after specific words

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

    late or forgetting chores

    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
    ımızı
    0.51
    谦
    0.51
     реши
    0.50
    ни
    0.50
    响起
    0.50
    ⃛
    0.49
    óln
    0.49
    ென
    0.49
     заседа
    0.48
     Отече
    0.48
    POSITIVE LOGITS
     halves
    0.51
     informatie
    0.49
     aswell
    0.49
     although
    0.48
     cương
    0.46
     turbines
    0.45
     hydrogens
    0.44
     ;\
    0.44
     trailers
    0.44
     ecz
    0.43
    Activations Density 0.001%

    No Known Activations