© 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. 197249
    Prev
    Next
    INDEX
    Explanations

    sentence starters

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

    navigating cash flow

    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
     අ
    0.53
    appings
    0.46
     میزان
    0.45
     تصور
    0.45
     ദു
    0.44
    了很多
    0.44
     ദ
    0.43
     Absatz
    0.42
     റ
    0.42
    hao
    0.41
    POSITIVE LOGITS
    ู
    0.49
    ू
    0.48
    ₺
    0.46
    𝐧
    0.46
    եմ
    0.46
    моби
    0.45
    ુ
    0.44
     probabil
    0.44
    ొక్క
    0.43
    ิจ
    0.43
    Activations Density 0.001%

    No Known Activations