© 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. 158979
    Prev
    Next
    INDEX
    Explanations

    used in different contexts

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

    psychologically identical or toxic family

    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
     বণ্টন
    0.60
     leases
    0.49
     expatri
    0.47
    }_{+}
    0.47
     Chưa
    0.46
     risks
    0.46
     divides
    0.45
     mögliche
    0.45
     Coverage
    0.44
     감소
    0.44
    POSITIVE LOGITS
    و
    0.55
    e
    0.50
    面
    0.49
    会場
    0.47
     геро
    0.46
    姩
    0.46
    说到
    0.45
    呜
    0.45
    程度上
    0.44
    なの
    0.43
    Activations Density 0.001%

    No Known Activations