© 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. 172574
    Prev
    Next
    INDEX
    Explanations

    specific nouns

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

    emotional states

    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
     pyl
    0.52
     fertilized
    0.47
     floors
    0.45
    :+
    0.44
     genetic
    0.43
     xyz
    0.43
    wp
    0.43
    iral
    0.42
     uplink
    0.42
     faq
    0.42
    POSITIVE LOGITS
    คัญ
    0.52
    новништво
    0.50
     competição
    0.48
     Букмекердик
    0.48
    arzy
    0.47
    셰
    0.46
     compétition
    0.45
    точ
    0.45
     Bühne
    0.45
    傩
    0.45
    Activations Density 0.001%

    No Known Activations