© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 116147
    Prev
    Next
    INDEX
    Explanations

    qualifications and experience

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

    skills and qualifications

    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
     recruiter
    0.48
    用来
    0.45
     recruiters
    0.43
     grocery
    0.43
     勺
    0.42
     workspace
    0.42
    лно
    0.42
     school
    0.42
     recruitment
    0.41
     toolbar
    0.41
    POSITIVE LOGITS
    佛教
    0.44
     Franc
    0.40
     Larger
    0.39
    蜚
    0.38
     misog
    0.38
    囝
    0.38
    Amb
    0.37
     Buddh
    0.37
     அரசியல்
    0.36
    되기
    0.36
    Activations Density 0.012%

    No Known Activations