© 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. 186682
    Prev
    Next
    INDEX
    Explanations

    locations and services

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

    desire for ties or freedom

    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
     demás
    0.48
    的价格
    0.47
    iky
    0.46
     cheeky
    0.46
    다면
    0.45
     protegido
    0.45
    omethyl
    0.45
    ກ
    0.44
    磋商
    0.44
     நடந்து
    0.43
    POSITIVE LOGITS
     maids
    0.56
     outsourcing
    0.53
     Nigeria
    0.52
     housekeeping
    0.49
     abord
    0.49
     nurses
    0.49
     elevators
    0.48
     establishments
    0.48
     overly
    0.47
     carers
    0.47
    Activations Density 0.001%

    No Known Activations