© 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. 33273
    Prev
    Next
    INDEX
    Explanations

    concepts followed by definite articles

    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
    прежнему
    0.46
    фото
    0.44
    ኾ
    0.44
     хоте
    0.42
     考え
    0.42
    хоро
    0.41
    حال
    0.41
     судь
    0.41
     intractable
    0.41
    맬
    0.41
    POSITIVE LOGITS
    ur
    0.53
     recurring
    0.46
     takip
    0.45
     precies
    0.45
     Poinc
    0.44
    ^{*}$.
    0.43
     sprinkler
    0.42
     bhi
    0.42
     sprink
    0.42
     celle
    0.42
    Activations Density 0.002%

    No Known Activations