© 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. 155361
    Prev
    Next
    INDEX
    Explanations

    filed under categories

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

    going on

    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
    ulen
    0.53
    atae
    0.50
    ї
    0.50
    ugd
    0.49
    ца
    0.49
    ái
    0.49
    kaa
    0.49
    ake
    0.48
    raa
    0.47
    є
    0.47
    POSITIVE LOGITS
     silenc
    0.47
     കൂടുതല്‍
    0.47
     săptăm
    0.47
     bardziej
    0.46
     paździer
    0.46
    㴓
    0.45
     globular
    0.45
     wyłącznie
    0.45
     steward
    0.44
     much
    0.44
    Activations Density 0.001%

    No Known Activations