© 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. 143296
    Prev
    Next
    INDEX
    Explanations

    love and relationships between people

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

    objective function, responsible, reasonable

    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
    ెల
    0.45
    рів
    0.45
    丕
    0.44
    OfType
    0.44
    ጾ
    0.44
    원본
    0.43
    Ἐ
    0.43
    θος
    0.43
    াস
    0.43
    ື
    0.43
    POSITIVE LOGITS
     kend
    0.55
     cheeks
    0.52
     limbo
    0.46
     eight
    0.46
     cleanse
    0.45
     smack
    0.45
     redd
    0.44
     antib
    0.44
    lique
    0.44
    க்காக
    0.44
    Activations Density 0.001%

    No Known Activations