© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2209
    Prev
    Next
    INDEX
    Explanations

    imagining and proposing ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     observance
    1.25
    铵
    1.24
    快樂
    1.19
    厄
    1.16
    快乐
    1.15
    品質
    1.14
    yawa
    1.12
    忙
    1.12
     DataType
    1.11
    记忆
    1.11
    POSITIVE LOGITS
     proposals
    2.30
     proposal
    2.21
     Proposals
    1.96
    proposal
    1.96
     Proposal
    1.93
     proposed
    1.91
     propuesta
    1.91
    Proposal
    1.88
    Proposed
    1.86
     ideas
    1.83
    Activations Density 0.921%

    No Known Activations