© 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. 136398
    Prev
    Next
    INDEX
    Explanations

    experiments and beta testing

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

    experiments and testing

    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
     acre
    0.46
     hydrocarbons
    0.46
     vrije
    0.44
     libres
    0.43
     acreage
    0.43
     jedin
    0.42
     producir
    0.41
     곡
    0.41
     duy
    0.41
    FREE
    0.41
    POSITIVE LOGITS
    Experiments
    0.57
    experiments
    0.56
     Experiments
    0.53
     experiments
    0.51
    Experiment
    0.51
    experiment
    0.50
    beta
    0.50
     Experiment
    0.49
     speriment
    0.49
     gradual
    0.48
    Activations Density 0.099%

    No Known Activations