© 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. 37900
    Prev
    Next
    INDEX
    Explanations

    in lieu of flowers

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

    instead of

    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
     isn
    0.45
     Brad
    0.45
     dissol
    0.45
     Tate
    0.45
     batch
    0.44
    $.
    0.42
     dashed
    0.42
     replace
    0.42
     birt
    0.42
     collapsed
    0.41
    POSITIVE LOGITS
     हुसैन
    0.46
    müşt
    0.45
    PRESSED
    0.45
    èces
    0.44
    éristique
    0.44
    茘
    0.44
    اکی
    0.44
    κών
    0.42
     franche
    0.42
     других
    0.42
    Activations Density 0.001%

    No Known Activations