© 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. 70780
    Prev
    Next
    INDEX
    Explanations

    words following certain phrases

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

    subconscious without roles communicates before cases branches

    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
     Riverside
    0.50
    Ch
    0.49
     Lü
    0.48
    For
    0.48
    2
    0.48
     L
    0.47
     Luca
    0.47
    สัม
    0.47
    Another
    0.46
    ق
    0.46
    POSITIVE LOGITS
    atenate
    0.52
    ianie
    0.50
    rai
    0.47
     nanoparticle
    0.44
     البنات
    0.43
    lance
    0.43
    micron
    0.43
    baud
    0.43
    ifolia
    0.42
    headlines
    0.41
    Activations Density 0.000%

    No Known Activations