© 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. 177472
    Prev
    Next
    INDEX
    Explanations

    title IV programs

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

    traditional recipe, chemical synthesis

    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
     dày
    0.46
     máu
    0.45
    <0xD2>
    0.44
    će
    0.44
    ала
    0.44
    संह
    0.43
    쭉
    0.43
    Б
    0.43
    ез
    0.43
    рб
    0.42
    POSITIVE LOGITS
    utiliser
    0.49
    rs
    0.49
    have
    0.44
    olit
    0.44
     bekannt
    0.44
     স্ম
    0.43
     raggiungere
    0.43
    org
    0.42
     Have
    0.41
     Electric
    0.41
    Activations Density 0.009%

    No Known Activations