© 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. 173660
    Prev
    Next
    INDEX
    Explanations

    process begins at block

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

    token limits and lengths

    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
    the
    0.49
     圆
    0.48
     lengthening
    0.44
    <0x95>
    0.43
     extension
    0.42
     ด
    0.42
     โอ
    0.42
    <0x93>
    0.41
    Extensions
    0.41
     genealogical
    0.41
    POSITIVE LOGITS
     म्हणूनच
    0.45
     poiché
    0.44
     Pogis
    0.44
     debido
    0.43
    Saldo
    0.42
     avuto
    0.42
     troviamo
    0.42
     lograr
    0.40
     фрук
    0.40
     Malgré
    0.40
    Activations Density 0.000%

    No Known Activations