© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62168
    Prev
    Next
    INDEX
    Explanations

    applying for, personalized, abilities, unconventional possibilities, Christian perspective, nature of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     femminile
    0.45
    括号
    0.43
    脸上
    0.41
     वॉइस
    0.40
     বছর
    0.39
     तुम्हाला
    0.39
     单位
    0.39
    钦
    0.39
    囩
    0.39
    动
    0.38
    POSITIVE LOGITS
     inhibiting
    0.43
     abort
    0.43
     accomplishes
    0.42
     immediately
    0.42
     labors
    0.42
    an
    0.41
     quickly
    0.41
     odmah
    0.40
     cepat
    0.40
    不但
    0.40
    Activations Density 0.011%

    No Known Activations