© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32815
    Prev
    Next
    INDEX
    Explanations

    Swedish conjunctions and prepositions

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

    märkning prägel bidrag

    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
    Not in Any Lists

    No Comments

    Negative Logits
     appellate
    0.60
     officials
    0.59
     caucus
    0.59
    ർ
    0.57
    َح
    0.56
     quarterbacks
    0.55
     antitrust
    0.55
     voicemail
    0.55
    ൺ
    0.55
     slaw
    0.55
    POSITIVE LOGITS
    På
    0.96
     När
    0.90
    För
    0.88
     Där
    0.88
     För
    0.86
     På
    0.84
    Så
    0.84
     då
    0.82
     Når
    0.79
     når
    0.79
    Activations Density 0.022%

    No Known Activations