© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6144
    Prev
    Next
    INDEX
    Explanations

    place name and noun pairs

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

    HOPE

    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_53_width_65k_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
    ।,
    0.40
    /////
    0.39
     ….
    0.39
    。.
    0.39
    icios
    0.38
    ached
    0.37
    洿
    0.37
    ۂ
    0.37
    iners
    0.37
    bG
    0.37
    POSITIVE LOGITS
     Decrease
    0.49
    XYGEN
    0.46
     Utilize
    0.46
     wrongdoing
    0.46
    গ্রন্থ
    0.44
    景象
    0.44
     autobus
    0.44
     uncooked
    0.43
     Fairness
    0.43
     rehearse
    0.43
    Activations Density 0.297%

    No Known Activations