© 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. 239442
    Prev
    Next
    INDEX
    Explanations

    trip looming

    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
    tablet
    0.52
    t
    0.51
    m
    0.51
    ardi
    0.49
    foon
    0.48
    temper
    0.48
    tis
    0.47
    OGRAM
    0.46
    rams
    0.46
    <b>
    0.46
    POSITIVE LOGITS
     frequency
    0.44
     brainstorm
    0.44
    ]()
    0.44
     zuf
    0.43
     พระเจ้า
    0.43
    ᱹ
    0.42
     disseminate
    0.42
     Heim
    0.41
     detects
    0.41
     encephal
    0.41
    Activations Density 0.000%

    No Known Activations