© 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. 35693
    Prev
    Next
    INDEX
    Explanations

    let alone

    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
     maaaring
    0.36
    please
    0.35
     மரிய
    0.35
    returns
    0.35
    board
    0.35
    也會
    0.34
     भाव
    0.34
    끔
    0.34
    েইন
    0.34
    િયો
    0.34
    POSITIVE LOGITS
     let
    1.58
    let
    1.07
     Let
    0.94
     LET
    0.89
    Let
    0.89
    何况
    0.88
     certainly
    0.86
     лет
    0.85
    遑
    0.82
     huống
    0.79
    Activations Density 0.006%

    No Known Activations