© 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. 43572
    Prev
    Next
    INDEX
    Explanations

    scheduling and duration

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

    reiterate information about other models

    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
    ਾਲ
    0.46
    荠
    0.46
     Ausnahme
    0.45
    㚘
    0.44
     Patrol
    0.44
     lipase
    0.43
     paprika
    0.42
     tank
    0.42
     patrol
    0.42
     Kraj
    0.42
    POSITIVE LOGITS
    श
    0.45
    lv
    0.44
     नि
    0.43
    d
    0.43
    スマートフォン
    0.42
    での
    0.42
    em
    0.41
     लहान
    0.41
    Subscription
    0.41
     pfs
    0.41
    Activations Density 0.000%

    No Known Activations