© 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. 12736
    Prev
    Next
    INDEX
    Explanations

    normal, under, spending, management, development

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

    OpenAI provides works

    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
     despise
    0.39
     humiliating
    0.35
     לא
    0.34
     shenanigans
    0.34
     hatred
    0.34
    🤬
    0.33
     retribution
    0.33
     murderous
    0.33
     horrors
    0.32
     humiliation
    0.32
    POSITIVE LOGITS
    ্যেষ্ঠ
    0.30
    <unused2164>
    0.27
    鲐
    0.27
    北京市
    0.27
     вскоре
    0.27
    参见
    0.26
     আবদুল্লাহ
    0.25
     často
    0.25
     আনুশকা
    0.25
     میراتھن
    0.24
    Activations Density 0.064%

    No Known Activations