© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 3199
    Prev
    Next
    INDEX
    Explanations

    sports and hobbies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     రిలీ
    0.65
     বাচ্চা
    0.63
     clump
    0.60
     தரும்
    0.59
    敌
    0.59
    নিবার
    0.59
    ophe
    0.58
     juicy
    0.57
    ^
    0.57
    刷新
    0.57
    POSITIVE LOGITS
     cycling
    1.32
     biking
    1.25
     kayaking
    1.23
     snowboarding
    1.18
     canoeing
    1.18
     skiing
    1.12
     bicycl
    1.11
     archery
    1.11
     rowing
    1.09
     Cycling
    1.06
    Activations Density 0.582%

    No Known Activations