© 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. 180994
    Prev
    Next
    INDEX
    Explanations

    forward selection, access to

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

    agents, shape, variation, data, control, websites, trust

    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
    ).
    0.48
    دت
    0.45
     elim
    0.45
    +
    0.45
     shang
    0.45
     ಲಾ
    0.44
     eliminate
    0.43
     confuse
    0.42
    둠
    0.42
    .
    0.42
    POSITIVE LOGITS
    a
    0.66
    s
    0.66
    an
    0.62
    e
    0.55
    aż
    0.54
    емых
    0.52
    aş
    0.51
    anego
    0.51
    ἓ
    0.50
    eh
    0.50
    Activations Density 0.000%

    No Known Activations