© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 949
    Prev
    Next
    INDEX
    Explanations

    important to note or remember

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    Unknown
    1.54
     tarda
    1.50
    未能
    1.49
    瀹
    1.47
     pozdě
    1.45
     tentativa
    1.42
     yanlış
    1.41
    蹉
    1.40
    Unable
    1.40
     unsuccessful
    1.38
    POSITIVE LOGITS
     Mind
    1.19
    mind
    1.17
     MIND
    1.15
     mind
    1.15
     think
    1.10
     vigilance
    1.09
     '#
    1.05
    NY
    1.04
    武器
    1.03
     consider
    1.03
    Activations Density 0.877%

    No Known Activations