© 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. 74119
    Prev
    Next
    INDEX
    Explanations

    bowing and kneeling

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

    basic, simplified explanations

    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
     اغ
    0.51
     (
    0.50
    realpath
    0.46
     '*.
    0.43
    es
    0.42
     exceptionally
    0.42
    Sd
    0.42
     (>
    0.40
     fruitless
    0.40
     dil
    0.40
    POSITIVE LOGITS
    㖅
    0.49
    聝
    0.47
    畯
    0.46
    なし
    0.45
    🙁
    0.45
    อน
    0.44
    धन
    0.44
    jería
    0.43
    🔫
    0.43
    તે
    0.42
    Activations Density 0.000%

    No Known Activations