© 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. 224267
    Prev
    Next
    INDEX
    Explanations

    instructions

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

    increasing growth and change

    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
     т
    0.45
    umiem
    0.43
     itself
    0.42
    ्मण
    0.42
     могат
    0.42
     எழுது
    0.42
     sportsbook
    0.41
    Ку
    0.41
    랗
    0.41
    )="
    0.40
    POSITIVE LOGITS
     нарушение
    0.44
    2
    0.44
     protrusions
    0.43
     לאחר
    0.43
     vomiting
    0.42
     нарушения
    0.42
    chette
    0.41
    禍
    0.41
     zusätzlichen
    0.40
     dialing
    0.40
    Activations Density 0.001%

    No Known Activations