© 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-65K
    7. 50120
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming contexts

    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_65k_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
     seven
    0.55
     s
    0.54
    }
    0.52
    ]
    0.52
     not
    0.51
     more
    0.50
    7
    0.50
     a
    0.50
    ENE
    0.48
     spur
    0.47
    POSITIVE LOGITS
    im
    0.53
    á
    0.52
    éz
    0.50
     яго
    0.48
    чем
    0.48
    აწილ
    0.48
    wij
    0.48
    сколько
    0.48
     édition
    0.47
    adine
    0.47
    Activations Density 0.002%

    No Known Activations