© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 650
    Prev
    Next
    INDEX
    Explanations

    said grimly

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

    hostile work environment

    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_53_width_65k_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
     યાદ
    0.44
     ditth
    0.42
    чил
    0.41
    तरे
    0.41
     pabbaj
    0.41
    ጭ
    0.41
    畑
    0.41
    ヘア
    0.40
    homogeneous
    0.40
     खोज
    0.39
    POSITIVE LOGITS
     Spike
    0.56
     spiking
    0.50
     spike
    0.48
    spike
    0.46
     living
    0.46
     Living
    0.43
     gen
    0.42
     spiked
    0.41
     LIVING
    0.41
    Sp
    0.40
    Activations Density 0.000%

    No Known Activations