© 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. 249005
    Prev
    Next
    INDEX
    Explanations

    knitting, military, portfolio, lists

    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
     आइसो
    0.48
     organes
    0.46
     affirme
    0.45
    دت
    0.45
     dedim
    0.44
     moteur
    0.42
    Cntr
    0.42
    簫
    0.42
     magnets
    0.42
     undeni
    0.41
    POSITIVE LOGITS
     Shouldn
    0.52
     List
    0.49
    ITIS
    0.48
    就可以了
    0.47
    ing
    0.46
     Selecting
    0.46
    List
    0.46
     We
    0.45
     All
    0.45
     Lately
    0.45
    Activations Density 0.002%

    No Known Activations