© 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. 192166
    Prev
    Next
    INDEX
    Explanations

    what questions and lists

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

    turbidity, leaders, pizzas, crowded

    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
    TOD
    0.46
    recated
    0.45
    RNB
    0.45
    MI
    0.44
    ).__
    0.44
    KG
    0.43
    andex
    0.43
     ಮಾಡುತ್ತ
    0.43
    V
    0.42
    WE
    0.42
    POSITIVE LOGITS
     experiential
    0.50
     tujuh
    0.50
     facilit
    0.49
     migli
    0.48
     fiets
    0.47
     hour
    0.47
     bastion
    0.46
     cinci
    0.46
     optimality
    0.46
     apprendre
    0.45
    Activations Density 0.000%

    No Known Activations