© 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. 705
    Prev
    Next
    INDEX
    Explanations

    modal verbs of possibility or capability

    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
     consistently
    1.60
    uar
    1.43
    _
    1.40
    lery
    1.37
     incess
    1.36
    removeAll
    1.33
     unequivocally
    1.31
    _'
    1.31
    ⓡ
    1.30
     constamment
    1.30
    POSITIVE LOGITS
     ciekaw
    1.76
    也可以
    1.74
    하기도
    1.70
     podríamos
    1.62
    也可
    1.61
     alternatively
    1.60
     Alternatively
    1.48
     belki
    1.45
    还可以
    1.40
    かもしれない
    1.38
    Activations Density 0.801%

    No Known Activations