© 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. 78257
    Prev
    Next
    INDEX
    Explanations

    Corinthians spiritual gifts

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

    speaking in tongues today

    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
    㫣
    0.42
     शाहिद
    0.39
    Acetoxy
    0.39
    巡
    0.39
     hatched
    0.38
    Lonely
    0.38
    넵
    0.38
     друзья
    0.38
     यमुना
    0.38
    룻
    0.38
    POSITIVE LOGITS
     Voluntary
    0.49
     Modal
    0.42
     Intelligence
    0.42
     Conj
    0.41
     RDS
    0.40
     Chair
    0.40
     Theater
    0.40
     suspending
    0.40
     Holder
    0.40
     Solver
    0.40
    Activations Density 0.046%

    No Known Activations