© 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. 223532
    Prev
    Next
    INDEX
    Explanations

    Holy God

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

    legal and business terms

    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
    งาน
    0.48
    REL
    0.48
    えた
    0.46
    DEF
    0.46
    낙
    0.45
    unn
    0.45
     दल
    0.45
    レイ
    0.45
    allas
    0.43
    云南
    0.43
    POSITIVE LOGITS
     BSC
    0.51
    )]
    0.50
     Hasbro
    0.49
     skim
    0.49
     AU
    0.49
     OU
    0.47
     gleichen
    0.47
     Ou
    0.47
     Mira
    0.47
     tanned
    0.47
    Activations Density 0.002%

    No Known Activations