© 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. 201873
    Prev
    Next
    INDEX
    Explanations

    hanging or built structures

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

    specific date; probability of rain

    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
     Свет
    0.50
     Holz
    0.47
     すご
    0.47
     Holog
    0.47
    细节
    0.46
    çou
    0.46
     πολι
    0.46
     便
    0.45
     Nası
    0.44
    妵
    0.44
    POSITIVE LOGITS
     fence
    0.44
    inds
    0.42
     rack
    0.41
     spending
    0.40
    اح
    0.40
     sump
    0.39
    cost
    0.39
    (
    0.38
    rhs
    0.38
     STOP
    0.38
    Activations Density 0.001%

    No Known Activations