© 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. 175253
    Prev
    Next
    INDEX
    Explanations

    various designs

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

    Romantic

    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
    OY
    0.50
     mobiles
    0.50
    કા
    0.49
     médicaments
    0.48
    レクトリ
    0.47
    眠
    0.47
    ンプ
    0.46
    絶対に
    0.46
    殴
    0.46
    Всем
    0.46
    POSITIVE LOGITS
    elevation
    0.48
    eket
    0.46
    deel
    0.45
     سبيل
    0.45
    belief
    0.45
     කැ
    0.45
    sha
    0.44
    receive
    0.44
    received
    0.44
    steiger
    0.43
    Activations Density 0.000%

    No Known Activations