© 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. 98684
    Prev
    Next
    INDEX
    Explanations

    actions and their direct consequences

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

    Increased demand or frequency

    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
     stabilizes
    0.45
    ।
    0.45
     impairs
    0.42
     embeds
    0.41
     embeddings
    0.40
     disbanded
    0.40
     đo
    0.39
     normalize
    0.39
    และการ
    0.39
     microbes
    0.38
    POSITIVE LOGITS
    豔
    0.50
    事故
    0.48
    סת
    0.45
    тын
    0.44
    accordo
    0.44
     attrezz
    0.44
    håll
    0.43
    organiser
    0.43
    蹿
    0.42
    琬
    0.42
    Activations Density 0.001%

    No Known Activations