© 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. 77507
    Prev
    Next
    INDEX
    Explanations

    marketing, affiliate, automation, search, snippet

    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
    ട
    0.52
    ॓
    0.52
    אן
    0.51
    ي
    0.51
     הולנד
    0.51
    ୮
    0.51
    ৤
    0.51
    Ι
    0.50
    ﻟ
    0.49
    ꔰ
    0.49
    POSITIVE LOGITS
     cutting
    0.49
     over
    0.45
     derivatives
    0.43
     unsound
    0.43
     directions
    0.43
     cuttings
    0.42
     ulcers
    0.41
     been
    0.41
     derivative
    0.41
     inevitable
    0.41
    Activations Density 0.000%

    No Known Activations