© 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. 31-GEMMASCOPE-2-RES-262K
    7. 21654
    Prev
    Next
    INDEX
    Explanations

    Use Case: serialization

    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_31_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
    ιδ
    0.47
    Ag
    0.42
    Charge
    0.40
    Ill
    0.38
    Bez
    0.38
    ท
    0.38
    क्योंकि
    0.38
    గ
    0.38
    ومی
    0.37
    մ
    0.37
    POSITIVE LOGITS
     feature
    0.43
     came
    0.43
     microphone
    0.43
     همچنین
    0.43
     then
    0.42
     preced
    0.41
     are
    0.41
     zatim
    0.41
     seasoned
    0.40
     member
    0.40
    Activations Density 0.002%

    No Known Activations