© 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. 37897
    Prev
    Next
    INDEX
    Explanations

    eternal punishment, hell, sin, Heaven, China

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

    Infrastructure Kit

    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
     turquoise
    0.51
     sapphire
    0.47
     goTo
    0.47
     besieged
    0.46
     torment
    0.46
     plaintext
    0.45
     mysterious
    0.44
     紫
    0.44
     volcanic
    0.43
     excavated
    0.43
    POSITIVE LOGITS
    I
    0.49
    İY
    0.49
    不及
    0.49
    N
    0.48
    *
    0.46
    Medicare
    0.46
    ❢
    0.45
    Hell
    0.45
    Dw
    0.45
     düşünüyorum
    0.44
    Activations Density 0.000%

    No Known Activations