© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1367
    Prev
    Next
    INDEX
    Explanations

    on and following words

    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_16k_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
     (|
    2.14
     has
    1.87
    ar
    1.82
    has
    1.76
     berada
    1.66
     kip
    1.65
    ⑪
    1.63
    ︎
    1.62
     had
    1.61
     acted
    1.60
    POSITIVE LOGITS
     behalf
    3.45
     terenie
    2.54
     grunn
    2.52
     podstawie
    2.21
    ething
    2.17
    ртуа
    2.16
    贄
    2.11
     stedet
    2.10
     základě
    2.05
    eday
    2.03
    Activations Density 0.252%

    No Known Activations