© 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. 73345
    Prev
    Next
    INDEX
    Explanations

    borrow, bore, loan

    np_acts-logits-general · gemini-2.5-flash-lite

    breeding practices, powerful productions, act with integrity

    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
     within
    0.50
     mamm
    0.48
    于是
    0.46
    十字
    0.44
     jigsaw
    0.44
     pus
    0.44
    驚
    0.44
     higher
    0.42
     surviv
    0.42
     locate
    0.42
    POSITIVE LOGITS
    loans
    0.60
    Loans
    0.53
    borrow
    0.53
    għ
    0.51
    tego
    0.50
    loan
    0.49
    ㅎ
    0.49
     ऋण
    0.49
    rechte
    0.49
     loans
    0.49
    Activations Density 0.000%

    No Known Activations