© 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. 78814
    Prev
    Next
    INDEX
    Explanations

    women, Medicare, factories, pp, ft

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

    literary contexts and fats

    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
    ፈ
    0.44
    ത്തേക്ക്
    0.44
    随即
    0.43
    创建一个
    0.41
     Determination
    0.41
     Dub
    0.40
    键
    0.40
    连续
    0.39
     произво
    0.39
     batch
    0.39
    POSITIVE LOGITS
     ২০১৮
    0.47
     expon
    0.44
     wraz
    0.43
     flott
    0.41
    NUM
    0.40
     แน
    0.40
     inklusive
    0.39
     入っ
    0.39
     നല്‍ക
    0.39
     folos
    0.39
    Activations Density 0.002%

    No Known Activations