© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 148184
    Prev
    Next
    INDEX
    Explanations

    SMS link group

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

    improving realism, high-quality text

    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
    ся
    0.51
    heated
    0.50
    深入
    0.46
    惰
    0.45
    <s>
    0.45
    ում
    0.45
    QS
    0.45
    ins
    0.44
    ष्टा
    0.44
    深
    0.44
    POSITIVE LOGITS
     Zanzibar
    0.60
     Gazi
    0.59
     পরেও
    0.56
     Erit
    0.56
     Auch
    0.55
     forage
    0.55
     Lobkowicz
    0.55
     eren
    0.54
     Erdogan
    0.54
    LOTREntity
    0.54
    Activations Density 0.000%

    No Known Activations