© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1982
    Prev
    Next
    INDEX
    Explanations

    get started

    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_65k_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
    for
    0.33
    '
    0.29
    (
    0.28
    4
    0.28
    2
    0.26
    ram
    0.26
    NR
    0.26
    (“
    0.26
    ]
    0.25
    ser
    0.25
    POSITIVE LOGITS
     rid
    0.90
     acquainted
    0.63
    Started
    0.57
     bogged
    0.53
     started
    0.53
     excited
    0.51
     Started
    0.50
     into
    0.50
     Rid
    0.46
     underway
    0.46
    Activations Density 0.167%

    No Known Activations