© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 192784
    Prev
    Next
    INDEX
    Explanations

    pairs of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     од
    0.39
    呚
    0.38
     kí
    0.38
     ard
    0.37
     acknowledging
    0.37
     रास्ता
    0.37
     maximal
    0.37
     schneller
    0.36
    în
    0.36
    Arm
    0.35
    POSITIVE LOGITS
    parser
    0.40
    დნენ
    0.39
    eling
    0.39
    積
    0.39
     Tatar
    0.39
    merich
    0.38
    deceased
    0.38
    水位
    0.38
    ಜ್ಯ
    0.38
    ნენ
    0.37
    Activations Density 0.000%

    No Known Activations