© 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. 154661
    Prev
    Next
    INDEX
    Explanations

    higher proportion

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

    ruling the; my word; her reasons

    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
     όλα
    0.51
     सार्वजनिक
    0.49
    менение
    0.47
     вда
    0.46
    stärke
    0.45
    𝗬
    0.45
     gás
    0.45
    િજા
    0.44
     TRANSACTION
    0.44
     алы
    0.44
    POSITIVE LOGITS
     assures
    0.50
    6
    0.48
     poorest
    0.47
    |"
    0.46
     emptied
    0.46
     Poor
    0.45
     terrified
    0.45
     corpses
    0.45
    5
    0.44
    ]"
    0.44
    Activations Density 0.000%

    No Known Activations