© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14216
    Prev
    Next
    INDEX
    Explanations

    contact directly using

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

    reinforcement learning

    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_16k_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
    伸
    0.46
    ”
    0.46
     E
    0.42
     Collective
    0.40
    剧
    0.40
     wer
    0.39
     Watching
    0.39
     Less
    0.38
     ouv
    0.38
    èvres
    0.38
    POSITIVE LOGITS
    нт
    0.56
    postal
    0.53
    ދު
    0.53
     вопроса
    0.52
    ಿಂತ
    0.49
     foodie
    0.48
    CompliancePolicy
    0.47
    გ
    0.47
    FileSize
    0.47
    жной
    0.46
    Activations Density 0.003%

    No Known Activations