© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75800
    Prev
    Next
    INDEX
    Explanations

    actions followed by prepositions or 'to'

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

    ransomware target value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     contradicted
    0.45
    த்தட்ட
    0.45
     sindaco
    0.44
     oficio
    0.44
     enfon
    0.43
     foglie
    0.42
    اہ
    0.42
     bigli
    0.42
    슭
    0.42
     договору
    0.41
    POSITIVE LOGITS
    ra
    0.53
    ak
    0.50
    imgur
    0.50
     motivations
    0.48
    roits
    0.48
    ida
    0.48
    otho
    0.47
    angle
    0.47
    olly
    0.46
    ands
    0.46
    Activations Density 0.001%

    No Known Activations