© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126449
    Prev
    Next
    INDEX
    Explanations

    Intellectual property, harmful exploitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }^{+}+\
    0.45
    مرة
    0.41
    ੱਕ
    0.39
    ToAction
    0.37
    Movie
    0.37
     ازاي
    0.37
    Man
    0.37
    濃
    0.37
    Shaw
    0.36
    канчи
    0.36
    POSITIVE LOGITS
     ergonomic
    0.48
     erroneous
    0.48
     bazaar
    0.47
     bipartite
    0.47
     nordic
    0.47
     unnecessary
    0.46
    тельный
    0.45
     plausible
    0.44
     adjoint
    0.44
     WLAN
    0.44
    Activations Density 0.007%

    No Known Activations