© 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. 89955
    Prev
    Next
    INDEX
    Explanations

    educational achievements and qualifications

    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
     :
    0.50
    r
    0.48
    rte
    0.48
    })
    0.47
    deeds
    0.47
    :
    0.46
    em
    0.45
    endo
    0.45
    })}{
    0.45
    ี่ป
    0.44
    POSITIVE LOGITS
     정책
    0.57
     සහ
    0.55
     సంస్థ
    0.51
     والف
    0.50
     როგორ
    0.49
     قیادت
    0.49
     நிறுவன
    0.48
     అత
    0.46
     było
    0.46
     नीति
    0.46
    Activations Density 0.001%

    No Known Activations