© 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. 222160
    Prev
    Next
    INDEX
    Explanations

    common grammatical structures

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

    emulation, plant, copied, poorly, practice, unofficial

    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
     सिंघ
    0.47
     kra
    0.46
    Zombie
    0.46
    relationship
    0.45
     thighs
    0.45
     ബ
    0.44
    <unused105>
    0.44
    <unused983>
    0.44
     ملك
    0.43
    <unused755>
    0.43
    POSITIVE LOGITS
    ిత
    0.44
    ப்ப
    0.42
    olées
    0.42
     Balm
    0.42
    nullptr
    0.41
     Arg
    0.41
     Greeting
    0.41
     প্রশ
    0.40
    కు
    0.40
    ོ
    0.40
    Activations Density 0.001%

    No Known Activations