© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 111877
    Prev
    Next
    INDEX
    Explanations

    identifying inventory, ABV, email, Hormone, clarity

    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
    ysis
    0.46
    ിട
    0.46
    Wat
    0.44
     گار
    0.43
    }}\
    0.43
    মতি
    0.43
    richtungen
    0.43
    ირი
    0.42
     거예요
    0.42
    )}.
    0.41
    POSITIVE LOGITS
     Method
    0.43
     as
    0.43
     recipe
    0.41
     Iodine
    0.41
     chemically
    0.40
     exacerbated
    0.40
     Prescription
    0.40
     giảm
    0.40
     convert
    0.39
     method
    0.39
    Activations Density 0.015%

    No Known Activations