© 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-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2845
    Prev
    Next
    INDEX
    Explanations

    holding or delayed states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     educativas
    0.92
     furnishings
    0.86
     standard
    0.82
    ,
    0.81
    וריה
    0.80
     curriculum
    0.80
     school
    0.80
     regulations
    0.79
    :
    0.78
     architectural
    0.77
    POSITIVE LOGITS
     Patience
    1.58
    diff
    1.45
     Delayed
    1.45
     DIFFER
    1.44
     WAIT
    1.44
     Buffered
    1.44
     Wait
    1.43
     Jara
    1.42
     Shift
    1.41
     Mercier
    1.41
    Activations Density 0.225%

    No Known Activations