© 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. 234039
    Prev
    Next
    INDEX
    Explanations

    planters are, focus on, three times

    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
    velyan
    0.47
    ਸ਼
    0.47
    ី
    0.46
    ΟΥ
    0.46
    分之一
    0.46
     每
    0.45
    一方で
    0.45
    withdrawal
    0.45
    푝
    0.45
    椃
    0.44
    POSITIVE LOGITS
     digitale
    0.52
     bli
    0.50
     grij
    0.49
     coaster
    0.46
     Ship
    0.45
     March
    0.45
     genü
    0.45
     dels
    0.45
     apari
    0.45
     LaF
    0.45
    Activations Density 0.000%

    No Known Activations