© 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. 125863
    Prev
    Next
    INDEX
    Explanations

    loan questions

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

    description of context

    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
     erstwhile
    0.51
    гатьох
    0.46
    м
    0.46
    huri
    0.45
     constitué
    0.45
    ingos
    0.44
     ні
    0.44
     ancien
    0.44
     physiologique
    0.44
    τια
    0.43
    POSITIVE LOGITS
    diction
    0.52
    ”
    0.46
    dict
    0.46
    性的
    0.45
     Pellegr
    0.45
    formatting
    0.44
    episode
    0.44
    reviewed
    0.43
    栻
    0.42
    বেদন
    0.41
    Activations Density 0.001%

    No Known Activations