© 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. 95309
    Prev
    Next
    INDEX
    Explanations

    produced for, Linked Navigation, president had

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

    calculator api, other ingredients

    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
    ছুর
    0.44
     (€
    0.44
     Rutherford
    0.40
    ավոր
    0.40
     Duluth
    0.40
    कीन
    0.40
    DataGridView
    0.39
    Transactional
    0.39
    €
    0.39
     €
    0.39
    POSITIVE LOGITS
    roveň
    0.52
    sources
    0.50
    I
    0.48
     coleta
    0.47
    čas
    0.45
     ক্ষমতা
    0.45
     δυνατό
    0.45
    ízo
    0.45
    debt
    0.44
     لاءِ
    0.44
    Activations Density 0.000%

    No Known Activations