© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3647
    Prev
    Next
    INDEX
    Explanations

    ongoing or future actions

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

    tokens that indicate continuation or ongoing/continuous action (words signaling something continues).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    1.79
    ’
    1.55
    1.38
    ،
    1.22
    \
    1.17
    、
    1.17
    ).
    1.08
    ı
    1.08
    \"
    1.05
    ,
    1.04
    POSITIVE LOGITS
    the
    1.98
    تي
    1.60
    r
    1.48
    на
    1.48
    n
    1.41
    توان
    1.35
    ر
    1.34
    is
    1.33
    u
    1.25
    to
    1.24
    Activations Density 0.087%

    No Known Activations