© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78806
    Prev
    Next
    INDEX
    Explanations

    earned points

    np_acts-logits-general · gemini-2.5-flash-lite

    emotional connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ম
    0.46
    准备
    0.45
    药物
    0.43
     זאת
    0.42
    다음
    0.42
    ی
    0.41
    장
    0.40
    బ
    0.40
    这一
    0.40
    Missense
    0.40
    POSITIVE LOGITS
     E
    0.53
     depreciation
    0.45
    idig
    0.45
     dint
    0.45
     চুরি
    0.44
     mortgages
    0.44
     HMRC
    0.44
     stoppage
    0.44
     maturities
    0.44
     EBITDA
    0.43
    Activations Density 0.000%

    No Known Activations