© 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. 112182
    Prev
    Next
    INDEX
    Explanations

    identity, failures, Black

    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
     garden
    0.48
     exchange
    0.47
     inferiores
    0.46
     lawn
    0.46
    BusinessType
    0.45
    P
    0.43
     gardens
    0.42
    Exchange
    0.42
     ます
    0.42
    কো
    0.42
    POSITIVE LOGITS
     тело
    0.49
    μεσα
    0.44
    èng
    0.44
     Teflon
    0.42
    lector
    0.42
    σταν
    0.42
    дея
    0.41
     Methodology
    0.41
    คาเด
    0.41
    <unused84>
    0.40
    Activations Density 0.003%

    No Known Activations