© 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. 34636
    Prev
    Next
    INDEX
    Explanations

    dumpster sizes

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

    conditional outcomes or past events

    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
    ِين
    0.49
    ט
    0.47
     prazer
    0.46
     xxx
    0.45
    лах
    0.44
    ុម
    0.44
    explique
    0.44
    ም
    0.43
     gusto
    0.42
    וט
    0.42
    POSITIVE LOGITS
     pitted
    0.46
     ब्रांड
    0.45
     creditor
    0.44
    इजेशन
    0.43
     लगातार
    0.43
     सेठ
    0.43
     utilized
    0.42
     सुर
    0.42
     famously
    0.42
     जिससे
    0.42
    Activations Density 0.000%

    No Known Activations