© 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. 157930
    Prev
    Next
    INDEX
    Explanations

    track down, account ID, birth certificate, fixed payment, olive oil, transformation

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

    software and academic terms

    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
    사
    0.57
    い
    0.55
    во
    0.55
    會
    0.55
    ব
    0.54
    Де
    0.54
    다
    0.53
    ر
    0.52
    воен
    0.52
    事務所
    0.51
    POSITIVE LOGITS
     Heroes
    0.55
     Tarantino
    0.53
     bailout
    0.52
     startled
    0.51
     Cal
    0.49
     Bigfoot
    0.49
     Natal
    0.49
     VIP
    0.48
     Sgt
    0.47
    acharya
    0.47
    Activations Density 0.000%

    No Known Activations