© 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. 137195
    Prev
    Next
    INDEX
    Explanations

    days, dates, or biblical references

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

    actions and intentions

    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
     பால
    0.48
    وی
    0.47
     노래
    0.47
    بازی
    0.46
     लहान
    0.45
    寯
    0.44
     করিতেছিল
    0.44
    アン
    0.44
    فیلم
    0.44
     બાળકો
    0.43
    POSITIVE LOGITS
     them
    0.51
     evil
    0.50
     megawatts
    0.48
     its
    0.48
     macht
    0.47
     kracht
    0.46
     willst
    0.45
     (=
    0.45
     власть
    0.44
     kijk
    0.44
    Activations Density 0.000%

    No Known Activations