© 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. 22292
    Prev
    Next
    INDEX
    Explanations

    memorization, Knob Pulls

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

    words in technical, legal, or historical contexts

    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
    ма
    0.68
    יל
    0.68
    ал
    0.66
    ור
    0.62
    יר
    0.61
    рав
    0.61
    리
    0.61
    아
    0.60
    фи
    0.60
    аб
    0.59
    POSITIVE LOGITS
     de
    0.55
     dos
    0.55
     en
    0.54
     vier
    0.54
     novos
    0.53
     roz
    0.53
     و
    0.52
     se
    0.52
     los
    0.51
     neue
    0.51
    Activations Density 0.195%

    No Known Activations