© 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. 138658
    Prev
    Next
    INDEX
    Explanations

    common phrases and words following

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

    danger and security risks

    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
    '
    0.49
     jest
    0.42
    lą
    0.41
     test
    0.40
    ’
    0.40
     tests
    0.40
    bis
    0.40
    '(
    0.39
    ]
    0.39
     scientific
    0.39
    POSITIVE LOGITS
    資本
    0.51
     capitalism
    0.45
     தற்போது
    0.43
    議員
    0.42
     सध्या
    0.40
     Capitalism
    0.40
     ilegal
    0.40
     unsustainable
    0.40
     প্রচলিত
    0.40
     माध्यमातून
    0.40
    Activations Density 0.000%

    No Known Activations