© 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. 68890
    Prev
    Next
    INDEX
    Explanations

    opposite directions

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

    Spanish endings (izada, iza) and context

    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
     bodily
    0.43
     bhikkhu
    0.43
    женности
    0.42
    -'].
    0.42
     Kerm
    0.42
     atypical
    0.41
     ophthal
    0.41
     handlerInput
    0.41
     accelerated
    0.41
     irritability
    0.40
    POSITIVE LOGITS
    izada
    0.55
    i
    0.51
    iza
    0.50
    amera
    0.46
    villa
    0.46
    ro
    0.46
    odeled
    0.46
    illa
    0.45
    ypso
    0.45
    ra
    0.44
    Activations Density 0.003%

    No Known Activations