© 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. 227841
    Prev
    Next
    INDEX
    Explanations

    New Hampshire theoretical discoveries

    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
     holomorphic
    0.46
     intestinal
    0.44
    -$
    0.43
     :(
    0.43
     connot
    0.42
     connotation
    0.42
     -(
    0.42
     implying
    0.42
    -:
    0.41
     :/
    0.41
    POSITIVE LOGITS
     હજાર
    0.54
     кры
    0.53
     Кры
    0.51
    ionais
    0.48
     Oso
    0.48
     вроде
    0.47
     आम
    0.46
     அதிகாரிகள்
    0.46
     Ось
    0.46
    不满
    0.45
    Activations Density 0.001%

    No Known Activations