© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112236
    Prev
    Next
    INDEX
    Explanations

    hard sci-fi, hard breach, hard work

    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_262k_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
     oficiais
    0.67
     roues
    0.66
    kę
    0.64
    বাহী
    0.63
    مک
    0.60
    서
    0.60
    एम
    0.59
     hutan
    0.59
    ünüz
    0.58
     rêves
    0.58
    POSITIVE LOGITS
     harder
    1.20
     hard
    1.20
    Hard
    1.19
     Hard
    1.14
    硬
    1.14
    hard
    1.13
     hardest
    0.99
     hardness
    0.98
     HARD
    0.98
     duro
    0.95
    Activations Density 0.051%

    No Known Activations