© 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. 144973
    Prev
    Next
    INDEX
    Explanations

    and we / and that we

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

    capturing this evolution

    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
    z
    0.54
    ="")
    0.54
    airport
    0.52
    ap
    0.52
    s
    0.51
    zné
    0.51
    r
    0.50
    ad
    0.50
    puri
    0.50
    ay
    0.50
    POSITIVE LOGITS
     juxtaposition
    0.57
     Aa
    0.52
     resignation
    0.47
     troph
    0.46
     Bt
    0.46
    麿
    0.45
     samb
    0.45
     shamb
    0.45
     combina
    0.44
     pervasive
    0.44
    Activations Density 0.002%

    No Known Activations