© 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. 168447
    Prev
    Next
    INDEX
    Explanations

    avoiding certain topics

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

    business professions and contracts

    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
    REACTOR
    0.60
     但
    0.51
     長財布
    0.51
     campo
    0.50
    ických
    0.50
     aparición
    0.50
    毯
    0.50
     serre
    0.49
     poema
    0.49
    坩
    0.48
    POSITIVE LOGITS
     motion
    0.48
     Laurence
    0.47
     hosts
    0.46
     proposition
    0.46
     experts
    0.45
     solutions
    0.43
     shareholders
    0.43
     Royal
    0.43
     adversary
    0.42
    บ
    0.42
    Activations Density 0.000%

    No Known Activations