© 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. 216744
    Prev
    Next
    INDEX
    Explanations

    night, special, development, they, toes

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

    subscription, musical, feelings, money

    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
     LOCCTR
    0.53
    ন্তু
    0.51
     dirigir
    0.50
     nahil
    0.48
     narrates
    0.48
     smiled
    0.48
    뀔
    0.48
     wasnt
    0.47
    ◠
    0.47
    レーター
    0.47
    POSITIVE LOGITS
    ια
    0.56
    iam
    0.52
    αι
    0.52
    vida
    0.47
    ne
    0.46
    iap
    0.46
    ի
    0.45
    iest
    0.45
    upid
    0.45
    是
    0.45
    Activations Density 0.000%

    No Known Activations