© 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. 96917
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

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

    negative outcomes

    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
     BSc
    0.48
     rr
    0.47
    old
    0.45
    time
    0.45
     XI
    0.44
     వే
    0.44
     Preprint
    0.44
     前
    0.43
     STI
    0.43
    erman
    0.43
    POSITIVE LOGITS
     skór
    0.52
     dérivés
    0.52
    Accueil
    0.51
     soumis
    0.50
    Musik
    0.50
     aussitôt
    0.50
     officielles
    0.49
     mécanismes
    0.49
     músicos
    0.48
     indígena
    0.47
    Activations Density 0.000%

    No Known Activations