© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110467
    Prev
    Next
    INDEX
    Explanations

    unanimous, certain, unknown, warnings

    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
    </footer>
    0.51
     firstNumber
    0.46
     മുഖ്യമന്ത്രി
    0.45
     प्रयोगशाला
    0.44
     लंबी
    0.43
     peč
    0.43
    協
    0.42
     tradizionale
    0.42
     provinsi
    0.42
    ște
    0.41
    POSITIVE LOGITS
    ist
    0.51
    ת
    0.51
    அ
    0.50
     deception
    0.49
     mislead
    0.48
    ர
    0.46
    스
    0.46
    ຜະລິດຕະພັນ
    0.46
    За
    0.45
     рукой
    0.45
    Activations Density 0.000%

    No Known Activations