© 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. 203244
    Prev
    Next
    INDEX
    Explanations

    conditions and consequences

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

    methods and options

    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
     Les
    0.50
     χ
    0.48
     Between
    0.46
    版权
    0.45
     Gatt
    0.45
     stubborn
    0.45
     Verlag
    0.45
    韋
    0.44
     Ζ
    0.43
    凊
    0.43
    POSITIVE LOGITS
     organelles
    0.50
    CTS
    0.49
    FDA
    0.48
    Cxt
    0.47
    CT
    0.46
     organe
    0.45
    EE
    0.44
     exploits
    0.44
     pioneers
    0.44
     campers
    0.44
    Activations Density 0.001%

    No Known Activations