© 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. 78287
    Prev
    Next
    INDEX
    Explanations

    starts words with 'a'

    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
    c
    0.48
     وتر
    0.47
    Fam
    0.46
    зва
    0.46
     warga
    0.45
    ka
    0.45
    ева
    0.45
    COMMAND
    0.44
     سنة
    0.44
    sulfanyl
    0.43
    POSITIVE LOGITS
    მწიფ
    0.47
    𒆷
    0.44
     countably
    0.42
    写作
    0.42
     gleiche
    0.42
     modernist
    0.42
    捲
    0.42
     Consid
    0.42
    এই
    0.42
     Analy
    0.42
    Activations Density 0.001%

    No Known Activations