© 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. 133540
    Prev
    Next
    INDEX
    Explanations

    competency, indicators, lbs, furniture

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

    organizational goals

    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
    𝔬
    0.54
     valut
    0.49
     evalu
    0.48
     tagReport
    0.48
    𝔞
    0.47
     seulement
    0.46
    ڈنگ
    0.45
     edilmesi
    0.44
     penjelasan
    0.44
     luglio
    0.44
    POSITIVE LOGITS
    起源
    0.48
    fted
    0.42
     schweren
    0.40
    後期
    0.40
    Invitrogen
    0.39
    削
    0.39
     изначально
    0.39
    火
    0.39
     штат
    0.39
    外的
    0.38
    Activations Density 0.000%

    No Known Activations