© 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. 2729
    Prev
    Next
    INDEX
    Explanations

    tech companies privacy risks

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

    safety guidelines and human reviewers

    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
     aquare
    0.53
     calcareous
    0.50
    itriangular
    0.48
    稈
    0.47
    稃
    0.47
    레
    0.47
     magnes
    0.47
     trypsin
    0.46
    盆
    0.46
     레
    0.46
    POSITIVE LOGITS
     Zuckerberg
    0.93
     Users
    0.86
     Tencent
    0.83
     users
    0.81
     Mozilla
    0.81
     Facebook
    0.79
     Nutzer
    0.79
    用户的
    0.78
     SaaS
    0.78
     उपयोगकर्ताओं
    0.77
    Activations Density 0.489%

    No Known Activations