© 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. 84466
    Prev
    Next
    INDEX
    Explanations

    locations in USA and Australia

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

    sequence indicators

    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
    ikiran
    0.47
    器
    0.45
    隸
    0.43
    竄
    0.43
    agd
    0.43
     増
    0.41
    ò
    0.41
    曳
    0.41
    増
    0.41
    իտ
    0.40
    POSITIVE LOGITS
     delectable
    0.52
     basé
    0.52
     basée
    0.46
     racing
    0.46
     dual
    0.45
     deoarece
    0.45
     glorie
    0.45
     selon
    0.44
     racer
    0.44
     enligt
    0.44
    Activations Density 0.000%

    No Known Activations