© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 125836
    Prev
    Next
    INDEX
    Explanations

    communication and preparation

    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
    problem
    0.46
     ESL
    0.44
    akrishnan
    0.44
    Pert
    0.43
    Mau
    0.43
    Scar
    0.41
     products
    0.40
     N
    0.40
     ATA
    0.40
     продав
    0.40
    POSITIVE LOGITS
    ओवर
    0.56
    ፦
    0.54
     forcible
    0.53
     পোক
    0.51
     prosegu
    0.49
    景象
    0.49
     bitOp
    0.48
    рого
    0.48
    ⤟
    0.48
     supersede
    0.48
    Activations Density 0.004%

    No Known Activations