© 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. 251315
    Prev
    Next
    INDEX
    Explanations

    situation send operator RSVP hid

    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
    vní
    0.46
    ését
    0.46
    áját
    0.44
    ुक
    0.44
    누
    0.42
    fälle
    0.42
    特
    0.41
    ských
    0.41
    ške
    0.41
    í
    0.41
    POSITIVE LOGITS
     blackmail
    0.53
     deceit
    0.47
     rescind
    0.47
     forum
    0.47
     NCAA
    0.47
     Hauptstadt
    0.47
     Dropbox
    0.46
     धोखा
    0.45
     Anschluss
    0.45
     Airlines
    0.45
    Activations Density 0.000%

    No Known Activations