© 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. 22775
    Prev
    Next
    INDEX
    Explanations

    "lpcm", "lithium battery", "liable for"

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

    words starting with L

    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
    t
    1.27
    r
    1.16
    la
    1.09
    il
    0.94
    c
    0.84
    ৩৮
    0.81
    j
    0.79
    lands
    0.78
    ২৯
    0.77
    land
    0.77
    POSITIVE LOGITS
    utenants
    1.16
    م
    1.11
    '
    1.08
    aky
    0.93
    )
    0.92
     a
    0.90
    า
    0.87
    ন
    0.85
    ),
    0.84
    SE
    0.82
    Activations Density 0.470%

    No Known Activations