© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60215
    Prev
    Next
    INDEX
    Explanations

    legal and code contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DBS
    -0.82
    IKAN
    -0.71
    UDIO
    -0.68
     Hippo
    -0.68
     Rebel
    -0.68
    馒头
    -0.68
    낵
    -0.68
    nue
    -0.68
    żu
    -0.66
     boule
    -0.65
    POSITIVE LOGITS
    ีย
    0.67
    esz
    0.65
    Bailey
    0.65
     включая
    0.63
     النبات
    0.63
     Bailey
    0.63
    hyp
    0.63
    孀
    0.63
    崎
    0.63
    遐
    0.61
    Activations Density 0.069%

    No Known Activations