© 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. 120735
    Prev
    Next
    INDEX
    Explanations

    additional costs, species recovery, FLY A JET

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

    emergent abilities and behaviors

    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
    INE
    0.54
     deadlines
    0.48
     underestimate
    0.48
     ignore
    0.48
     overestimate
    0.47
    IVING
    0.47
    વાડી
    0.46
     먼
    0.44
    vić
    0.43
    IGNORE
    0.43
    POSITIVE LOGITS
     logiciel
    0.57
    なく
    0.54
    𝕤
    0.54
    زام
    0.53
    سوم
    0.49
    靱
    0.48
    اری
    0.47
    ابی
    0.47
     maîtres
    0.46
     сер
    0.46
    Activations Density 0.001%

    No Known Activations