© 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. 88335
    Prev
    Next
    INDEX
    Explanations

    so... meaning, implication, or consequence

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

    sentences beginning with 'So,'

    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
    ご
    0.44
    आइए
    0.43
     voici
    0.42
    কলার
    0.42
     vamos
    0.41
     sådan
    0.40
     دیکھتے
    0.40
     pacote
    0.39
    まつ
    0.39
     mh
    0.39
    POSITIVE LOGITS
     implying
    0.42
    这意味着
    0.41
    ńcz
    0.41
     Ent
    0.41
    ent
    0.40
    ျ
    0.40
    的感觉
    0.39
    ovel
    0.39
     implication
    0.39
     Meaning
    0.38
    Activations Density 0.020%

    No Known Activations