© 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. 221926
    Prev
    Next
    INDEX
    Explanations

    market factors

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

    states or conditions after certain words

    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
     affidavits
    0.46
     referrals
    0.45
     Herrn
    0.43
     Referral
    0.43
     Histories
    0.43
    믄
    0.42
     ocurrido
    0.42
    狛
    0.42
    പ്പ
    0.41
     transcribed
    0.41
    POSITIVE LOGITS
    ressing
    0.44
    BURY
    0.44
    tourism
    0.44
    ag
    0.43
    chedelic
    0.43
    tting
    0.42
     चैन
    0.42
    av
    0.42
    qquad
    0.41
    𝑭
    0.41
    Activations Density 0.003%

    No Known Activations