© 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. 161371
    Prev
    Next
    INDEX
    Explanations

    outcomes and consequences

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

    face of, they are, damage to

    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
    ेंस
    0.51
     Zentrum
    0.50
    älj
    0.49
     заяв
    0.49
     دنبال
    0.48
    vět
    0.48
     attività
    0.48
     됐
    0.47
     vormen
    0.47
    ès
    0.47
    POSITIVE LOGITS
    蠶
    0.46
    皤
    0.45
     Clearly
    0.45
    留言
    0.43
    ウォ
    0.43
     নল
    0.42
     Logout
    0.42
     Also
    0.42
    姓名
    0.42
     May
    0.41
    Activations Density 0.000%

    No Known Activations